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. 7157
    Prev
    Next
    INDEX
    Explanations

    colons/quotes

    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
    ߥ
    -0.08
    تنسيق
    -0.08
    _numero
    -0.07
     הזכ
    -0.07
    酂
    -0.07
     document
    -0.07
     Nuevo
    -0.07
    ocator
    -0.07
    icens
    -0.07
     fine
    -0.07
    POSITIVE LOGITS
     HB
    0.07
    pra
    0.07
     uri
    0.07
     Aer
    0.06
    (parser
    0.06
    הת
    0.06
     해
    0.06
    iera
    0.06
     frees
    0.06
    routing
    0.06
    Activations Density 0.086%

    No Known Activations