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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 71459
    Prev
    Next
    INDEX
    Explanations

    import

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rape
    -0.07
    adapt
    -0.07
    /general
    -0.07
    height
    -0.07
    𝖊
    -0.07
    记忆力
    -0.07
     Problem
    -0.07
     getLast
    -0.07
    Merchant
    -0.07
    อำนาจ
    -0.07
    POSITIVE LOGITS
    Sha
    0.07
     multin
    0.07
     Broker
    0.07
    -K
    0.07
     biết
    0.07
    奖
    0.06
    Pont
    0.06
     tier
    0.06
    小伙伴
    0.06
    ]|
    0.06
    Activations Density 0.002%

    No Known Activations