© 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. 25-TRANSCODER-HP
    7. 107120
    Prev
    Next
    INDEX
    Explanations

    human

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Ness
    -0.27
    rut
    -0.27
    isch
    -0.26
     aim
    -0.26
    人类
    -0.25
     personal
    -0.25
    åIJĥäºı
    -0.25
    个人
    -0.25
     RFC
    -0.25
     mutually
    -0.24
    POSITIVE LOGITS
    åĨĻéģĵ
    0.27
    eness
    0.26
    -readable
    0.26
    åģ¥åº·ç®¡çIJĨ
    0.25
    bove
    0.25
     Mourinho
    0.25
     playable
    0.24
    温æļĸ
    0.24
    viron
    0.23
    obody
    0.23
    Activations Density 1.092%

    No Known Activations