© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 85722
    Prev
    Next
    INDEX
    Explanations

    Symbols and URLs

    np_max-act · gemini-2.0-flash

    specialized, domain-specific terms and category labels—often proper nouns or technical jargon—such as department names, locations, and technical computing topics.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    荆州
    -0.07
     الماضي
    -0.07
    地面
    -0.07
    UpInside
    -0.06
     Pond
    -0.06
    قطع
    -0.06
     butto
    -0.06
     scholarships
    -0.06
     מתאים
    -0.06
    キャン
    -0.06
    POSITIVE LOGITS
    overview
    0.07
    ();↵↵↵
    0.07
    ATE
    0.07
    _al
    0.07
    ANGER
    0.07
    _GOOD
    0.07
    𝐇
    0.07
    (flag
    0.07
    的就是
    0.07
     Niger
    0.06
    Activations Density 8.287%

    No Known Activations