© 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. 41028
    Prev
    Next
    INDEX
    Explanations

    code, markup, syntax

    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
    Negative Logits
     Lama
    -0.28
    ÑģÑĤолÑĮ
    -0.28
     L
    -0.28
    oller
    -0.28
    åIJ´
    -0.27
     ATA
    -0.27
    Filed
    -0.26
    gL
    -0.26
    _l
    -0.26
     LP
    -0.25
    POSITIVE LOGITS
     vig
    0.32
    uds
    0.25
    rief
    0.24
    ãĥĻãĥ³
    0.24
    Chem
    0.24
    丹
    0.23
    ç»Ŀç¼ĺ
    0.23
    _tex
    0.23
     Ch
    0.23
     Sed
    0.23
    Activations Density 0.012%

    No Known Activations