Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45334
    Prev
    Next
    INDEX
    Explanations

    scientific research/climate debate

    np_max-act · gemini-2.0-flash
    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
    中
    -0.08
     الن
    -0.07
    ن
    -0.07
    炼
    -0.07
    可行
    -0.07
     Comprehensive
    -0.07
     chặt
    -0.07
    丽江
    -0.07
    ypsum
    -0.07
     Developing
    -0.07
    POSITIVE LOGITS
     IDs
    0.07
    ڭ
    0.07
     horrified
    0.07
     cmdline
    0.07
    تغي
    0.06
    Rotation
    0.06
    팟
    0.06
    _BC
    0.06
    reatment
    0.06
    颥
    0.06
    Activations Density 0.051%

    No Known Activations