© 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. 19-RESID-POST-AA
    11. 69480
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    .Mode
    -0.07
    /memory
    -0.07
    耗费
    -0.07
    Velocity
    -0.07
     بت
    -0.07
     Led
    -0.06
     utiliz
    -0.06
     אמיתי
    -0.06
    成功率
    -0.06
     rte
    -0.06
    POSITIVE LOGITS
    儡
    0.07
    习近平
    0.07
    ǒ
    0.06
    (:,
    0.06
     meals
    0.06
    铛
    0.06
    敷
    0.06
     weer
    0.06
    _comm
    0.06
     Giới
    0.06
    Activations Density 0.014%

    No Known Activations