© 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. 12-TRANSCODER-HP
    7. 22023
    Prev
    Next
    INDEX
    Explanations

    Research or web text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     auto
    -0.30
    wei
    -0.29
    微信åı·
    -0.28
    spot
    -0.27
     ow
    -0.27
    auto
    -0.27
    客
    -0.27
     wei
    -0.26
     stable
    -0.25
     di
    -0.25
    POSITIVE LOGITS
    -transparent
    0.28
    èĥĦ
    0.26
    ä¸Ĭåİ»
    0.26
    $con
    0.25
     conform
    0.25
    èĵĦ
    0.25
    eneg
    0.25
    .querySelectorAll
    0.24
    ampp
    0.24
    udded
    0.24
    Activations Density 0.000%

    No Known Activations