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. 2745
    Prev
    Next
    INDEX
    Explanations

    ');

    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
    <O
    -0.07
    _mgr
    -0.07
    月末
    -0.07
     hello
    -0.07
    久しぶり
    -0.07
    🍆
    -0.07
    之初
    -0.06
    初二
    -0.06
     Into
    -0.06
     bụng
    -0.06
    POSITIVE LOGITS
     LEGO
    0.07
    roduced
    0.07
    fine
    0.07
     calcul
    0.07
    轮胎
    0.07
     contamin
    0.06
     Sidd
    0.06
    missible
    0.06
     structured
    0.06
     Lahore
    0.06
    Activations Density 0.021%

    No Known Activations