© 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. 40586
    Prev
    Next
    INDEX
    Explanations

    period

    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
    fbe
    -0.25
     undesirable
    -0.24
    çݯ
    -0.24
    _CALLBACK
    -0.24
    å±ķä½į
    -0.23
    SUB
    -0.23
    éĹ»è¨Ģ
    -0.23
    pch
    -0.23
    æ³µ
    -0.23
    utta
    -0.23
    POSITIVE LOGITS
    对éĿ¢
    0.28
    zyst
    0.24
     cz
    0.23
     Genetics
    0.23
     ..."↵↵
    0.23
    æħĪ
    0.23
    ivor
    0.23
    ofday
    0.23
     cram
    0.23
     mint
    0.23
    Activations Density 0.851%

    No Known Activations