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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 23000
    Prev
    Next
    INDEX
    Explanations

    imo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ꜥ
    -0.07
    厾
    -0.07
    开幕
    -0.07
     автоматы
    -0.07
    뤄
    -0.07
     extent
    -0.07
     StreamLazy
    -0.07
     Scottish
    -0.06
    ﭶ
    -0.06
     ascertain
    -0.06
    POSITIVE LOGITS
    <p
    0.08
    psych
    0.08
     disproportionately
    0.08
    _binary
    0.08
    食品药品
    0.08
     Psychiatry
    0.07
    た
    0.07
    _unique
    0.07
    <tr
    0.07
    共创
    0.07
    Activations Density 0.018%

    No Known Activations