Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 89192
    Prev
    Next
    INDEX
    Explanations

    conquer

    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
    .Screen
    -0.08
    ⼩
    -0.08
    列出
    -0.07
     galaxy
    -0.07
    年度
    -0.07
    ��이
    -0.07
    穴
    -0.07
    udden
    -0.07
    的相关
    -0.07
     Vue
    -0.07
    POSITIVE LOGITS
    ĥ
    0.08
    call
    0.07
     חיפה
    0.07
    城
    0.07
    Advisor
    0.06
    ﰁ
    0.06
     мира
    0.06
    AccessorType
    0.06
    .Br
    0.06
    Τ
    0.06
    Activations Density 0.007%

    No Known Activations