© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40884
    Prev
    Next
    INDEX
    Explanations

    origins and explanations

    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
    ÃŃc
    -0.28
    uent
    -0.26
    angible
    -0.25
    mom
    -0.25
    luent
    -0.25
    icing
    -0.25
     whistle
    -0.24
    æĬĽ
    -0.24
    สาย
    -0.23
     Weinstein
    -0.23
    POSITIVE LOGITS
    为äºĨ
    0.29
     inform
    0.28
     congratulate
    0.28
     \"{
    0.27
    ci
    0.27
    ocy
    0.27
    带ä¸Ĭ
    0.26
    ija
    0.26
    çĤºäºĨ
    0.26
    é¢Ķ
    0.26
    Activations Density 1.285%

    No Known Activations