© 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. 41231
    Prev
    Next
    INDEX
    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
    oge
    -0.30
     discharged
    -0.26
     jogging
    -0.26
    _KEYS
    -0.26
    [keys
    -0.26
    ä¸ĭæīĭ
    -0.26
    :event
    -0.24
    æ²¹èĦĤ
    -0.24
    åħ¬æ°ij
    -0.24
    authority
    -0.23
    POSITIVE LOGITS
    webElementProperties
    0.28
     ÑĢаÑģпÑĢоÑģÑĤ
    0.25
     <!--[
    0.25
    ÅĽÄĩ
    0.25
    RunWith
    0.25
    pref
    0.24
    rouw
    0.24
    core
    0.24
    æł¡å¤ĸ
    0.24
    tern
    0.24
    Activations Density 0.721%

    No Known Activations