© 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. 24237
    Prev
    Next
    INDEX
    Explanations

    1

    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
    éķľåŃIJ
    -0.29
    quete
    -0.27
    otonin
    -0.26
    å¿łå®ŀ
    -0.26
    æĻĴ
    -0.26
    IEW
    -0.24
    stÄĻp
    -0.24
    VAS
    -0.24
    ä¸įåıĬ
    -0.24
     doping
    -0.24
    POSITIVE LOGITS
    à°³
    0.27
    å°±æĺ¯åľ¨
    0.27
    .fm
    0.25
    ãģĮãĤī
    0.25
    _LO
    0.25
    acha
    0.25
    çĶ³
    0.24
    åĽłä¸ºæĪij
    0.24
    声
    0.24
    ency
    0.24
    Activations Density 0.004%

    No Known Activations