© 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. 25-TRANSCODER-HP
    7. 109301
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Bounty
    -0.24
     _|
    -0.24
    è¿Ļ个åIJįåŃĹ
    -0.24
    Ĺı
    -0.23
    bard
    -0.23
    "io
    -0.23
    ç«£
    -0.23
     pat
    -0.23
    èĹģ
    -0.23
     Ipsum
    -0.22
    POSITIVE LOGITS
    plevel
    0.28
    ä¸Ģä½ĵ
    0.26
    immer
    0.25
    eb
    0.25
    /sources
    0.25
    abytes
    0.24
    å¤ļå¹´
    0.24
    -present
    0.23
    ä¸ĥå¹´
    0.23
    åĩĨå¤ĩ
    0.23
    Activations Density 0.159%

    No Known Activations