© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56649
    Prev
    Next
    INDEX
    Explanations

    correctional facilities/legal cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸¤å¼ł
    -0.28
    ç®Ģ便
    -0.24
    amo
    -0.24
     iconName
    -0.24
     Sadd
    -0.24
    åĿ·
    -0.23
    ä»
    -0.23
    idd
    -0.23
    活泼
    -0.23
    åĩłå¼ł
    -0.23
    POSITIVE LOGITS
    hei
    0.29
    Bracket
    0.25
    æĸ¯åŁº
    0.25
    <System
    0.24
    \Log
    0.24
    -style
    0.24
    orsk
    0.23
     recall
    0.23
    èķ¨
    0.23
    ãĤīãģı
    0.23
    Activations Density 0.015%

    No Known Activations