© 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. 32-TRANSCODER-HP
    7. 41122
    Prev
    Next
    INDEX
    Explanations

    code and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĿ©
    -0.28
     WAL
    -0.27
     rever
    -0.27
    PGA
    -0.27
     Microsystems
    -0.26
    ihan
    -0.26
    壯
    -0.26
    _principal
    -0.25
    ÑĦоÑĢ
    -0.25
     Venez
    -0.24
    POSITIVE LOGITS
     N
    0.31
    *N
    0.29
    (N
    0.29
    "N
    0.29
    N
    0.28
    hot
    0.27
     Isis
    0.27
    è°Īèµ·
    0.27
    Hot
    0.27
    åĩ¼
    0.26
    Activations Density 0.000%

    No Known Activations