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. 71420
    Prev
    Next
    INDEX
    Explanations

    coding imports

    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
     Quint
    -0.08
    容忍
    -0.07
    ánd
    -0.07
    Tween
    -0.07
    总面积
    -0.07
     Apr
    -0.07
     Las
    -0.07
    נר
    -0.06
     tại
    -0.06
    /Product
    -0.06
    POSITIVE LOGITS
    旋律
    0.07
     overhe
    0.07
     stamped
    0.07
    extr
    0.07
    핱
    0.07
     probably
    0.06
    焐
    0.06
    控制
    0.06
    Ref
    0.06
    Still
    0.06
    Activations Density 0.007%

    No Known Activations