© 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. 31-TRANSCODER-HP
    7. 17915
    Prev
    Next
    INDEX
    Explanations

    Coding/programming imports packages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éļĨ
    -0.37
    åIJĦè¡Į
    -0.26
     proceeding
    -0.26
    bling
    -0.25
    rots
    -0.25
    éĺŁåijĺ们
    -0.25
     collisions
    -0.25
    Elements
    -0.24
    秩åºı
    -0.24
    带头人
    -0.23
    POSITIVE LOGITS
    s
    0.38
    iae
    0.34
    å°ij
    0.33
    arius
    0.30
    iosa
    0.27
    è¯ģ
    0.27
    ioso
    0.26
    hek
    0.26
    rier
    0.25
    iasm
    0.25
    Activations Density 0.002%

    No Known Activations