© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 1186
    Prev
    Next
    INDEX
    Explanations

    Academic/technical descriptions

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ܫ
    -0.08
    ؿ
    -0.07
     Everyday
    -0.07
    ⾨
    -0.07
    报酬
    -0.07
    出资
    -0.07
    _PE
    -0.07
     Simpson
    -0.07
     Sant
    -0.07
    💏
    -0.07
    POSITIVE LOGITS
    用户的
    0.09
    已经
    0.07
     cro
    0.07
    ＆
    0.07
     CUR
    0.07
    (GUI
    0.07
    教训
    0.07
    给她
    0.07
    gars
    0.06
     rejecting
    0.06
    Activations Density 0.322%

    No Known Activations