© 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
    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. 30325
    Prev
    Next
    INDEX
    Explanations

    it the

    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
     Engines
    -0.07
     Sor
    -0.07
    บำ
    -0.07
     Fresh
    -0.07
     Boat
    -0.07
     chops
    -0.07
    隰
    -0.07
    镶
    -0.06
     Hess
    -0.06
    	js
    -0.06
    POSITIVE LOGITS
    .Un
    0.07
    REQ
    0.07
    反倒
    0.07
    .OrderBy
    0.07
    不免
    0.06
     mun
    0.06
    _tp
    0.06
     duyệt
    0.06
    _N
    0.06
    肉体
    0.06
    Activations Density 0.034%

    No Known Activations