© 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. 11-RESID-POST-AA
    11. 62191
    Prev
    Next
    INDEX
    Explanations

    Numbers containing 1

    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
    十佳
    -0.08
    吐
    -0.07
     Tweets
    -0.07
     specific
    -0.07
    再也没有
    -0.07
     khắp
    -0.07
    嚼
    -0.07
    诗人
    -0.07
    WEBPACK
    -0.06
    FORMAT
    -0.06
    POSITIVE LOGITS
     flowed
    0.07
    cae
    0.06
    神话
    0.06
     paired
    0.06
    ガイ
    0.06
    很难
    0.06
    淏
    0.06
    世界观
    0.06
    <div
    0.06
    pragma
    0.06
    Activations Density 0.001%

    No Known Activations