© 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. 23-TRANSCODER-HP
    7. 25256
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åīįæĸ¹
    -0.30
     MOST
    -0.27
    inery
    -0.26
    嵩
    -0.26
    è¿Ļ家åħ¬åı¸
    -0.25
    .classes
    -0.25
    åı¦å¤ĸä¸Ģ个
    -0.24
    Going
    -0.24
    alore
    -0.24
    igest
    -0.24
    POSITIVE LOGITS
     til
    0.28
    Ñĩки
    0.24
    oir
    0.24
     Atlantic
    0.24
    åŁİå¸Ĥ建设
    0.24
     haz
    0.23
    lord
    0.23
    antz
    0.23
    .Err
    0.22
    رÙĪÙħ
    0.22
    Activations Density 0.048%

    No Known Activations