© 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. 22-TRANSCODER-HP
    7. 87482
    Prev
    Next
    INDEX
    Explanations

    Species/genus names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hou
    -0.32
     <![
    -0.25
    INDOW
    -0.24
    htable
    -0.24
    itty
    -0.23
    ilities
    -0.23
    stry
    -0.23
    uetype
    -0.23
    icut
    -0.23
    Dou
    -0.23
    POSITIVE LOGITS
    _Version
    0.25
    iot
    0.24
    太快
    0.23
    æĥħ
    0.23
    iolet
    0.23
     ag
    0.23
    repid
    0.23
    廪
    0.23
    анÑĤ
    0.23
    éĴ»
    0.22
    Activations Density 0.048%

    No Known Activations