© 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. 69465
    Prev
    Next
    INDEX
    Explanations

    .OrderBy or .Where

    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
    interesting
    -0.07
    setMax
    -0.07
     hung
    -0.07
    >a
    -0.07
    跳
    -0.07
    试
    -0.07
     strang
    -0.07
    拉
    -0.07
    挑
    -0.07
    弹
    -0.07
    POSITIVE LOGITS
    民意
    0.08
    _HTML
    0.07
     העוב
    0.07
     вокруг
    0.07
    ahu
    0.07
    不可缺少
    0.07
    حتياجات
    0.07
     asympt
    0.07
    随处可见
    0.07
    ༺
    0.07
    Activations Density 0.003%

    No Known Activations