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. 6786
    Prev
    Next
    INDEX
    Explanations

    changed

    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
    出国留学
    -0.07
     규정
    -0.07
    _PRINT
    -0.07
     biomass
    -0.07
    ⏎
    -0.06
    机床
    -0.06
    .Filter
    -0.06
    (rng
    -0.06
     jsonify
    -0.06
     Binder
    -0.06
    POSITIVE LOGITS
    -generation
    0.08
     success
    0.08
     class
    0.07
    긑
    0.07
    тики
    0.07
    _DU
    0.07
    bones
    0.06
    Cam
    0.06
     updated
    0.06
    Delivery
    0.06
    Activations Density 0.018%

    No Known Activations