© 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. 14-TRANSCODER-HP
    7. 41467
    Prev
    Next
    INDEX
    Explanations

    Internet/programming text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adian
    -0.34
    éĨĭ
    -0.29
    adians
    -0.27
    声éģĵ
    -0.27
    åĩºäºİ
    -0.25
    é¢ij
    -0.25
    æ¤į
    -0.24
    çĢļ
    -0.24
    elijk
    -0.24
    udd
    -0.23
    POSITIVE LOGITS
     previously
    0.27
    qml
    0.26
    ["_
    0.25
    MBER
    0.25
    lé
    0.25
    annes
    0.25
    UIApplication
    0.24
    oblin
    0.23
    代çIJĨ人
    0.23
    æĪĺ士æĿ¥è¯´
    0.23
    Activations Density 0.865%

    No Known Activations