© 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. 22146
    Prev
    Next
    INDEX
    Explanations

    in

    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
    _Space
    -0.28
    .nz
    -0.25
    assis
    -0.25
     accumulator
    -0.25
     space
    -0.25
     floral
    -0.25
    空éĹ´
    -0.25
    space
    -0.25
    excel
    -0.24
     unavoid
    -0.24
    POSITIVE LOGITS
     baud
    0.29
     Mercury
    0.27
    (bus
    0.25
    ứng
    0.25
    iais
    0.24
     Heard
    0.24
    ç»İ
    0.24
    æĮ«
    0.24
    äº
    0.24
    infer
    0.24
    Activations Density 0.008%

    No Known Activations