© 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. 40727
    Prev
    Next
    INDEX
    Explanations

    Motion, activity

    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
    ardin
    -0.29
    åĴĮå¹³
    -0.28
    .Lang
    -0.27
    椿
    -0.25
    èĢĥéªĮ
    -0.25
    imators
    -0.25
    cla
    -0.24
     Ston
    -0.24
    isode
    -0.23
    æĪ®
    -0.23
    POSITIVE LOGITS
    æĴ¥
    0.28
     Rae
    0.26
    æĭ¨
    0.25
    çĸı
    0.24
     logger
    0.24
     arranging
    0.24
    asp
    0.24
    ecc
    0.24
    .ylabel
    0.24
    èĬ±éĴ±
    0.24
    Activations Density 0.246%

    No Known Activations