© 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. 22061
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     generalize
    -0.35
     general
    -0.32
    general
    -0.29
     generalized
    -0.29
     général
    -0.29
    åIJģ
    -0.26
     Tracks
    -0.26
     tro
    -0.26
     sor
    -0.26
    éģµ
    -0.26
    POSITIVE LOGITS
    Catch
    0.28
    .catch
    0.28
    说æĺİ书
    0.28
    è¾¹ç¼ĺ
    0.27
    stown
    0.26
     Catch
    0.26
     inventor
    0.26
    DataContract
    0.25
    -corner
    0.25
    è¿ĻäºĽä¸ľè¥¿
    0.25
    Activations Density 0.029%

    No Known Activations