© 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. 22125
    Prev
    Next
    INDEX
    Explanations

    website 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
    lice
    -0.31
    loy
    -0.30
     Ding
    -0.28
    æĹº
    -0.27
    -dev
    -0.25
    loys
    -0.25
    tridge
    -0.25
    åº
    -0.25
    IEW
    -0.24
     ding
    -0.24
    POSITIVE LOGITS
    mits
    0.26
     exposures
    0.25
    caffe
    0.24
    ç¡Ĵ
    0.24
    tera
    0.24
    åį³ä½¿æĺ¯
    0.24
    空åīį
    0.24
    ERAL
    0.24
    ä¸įåĥı
    0.23
    baugh
    0.23
    Activations Density 0.000%

    No Known Activations