© 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. 23-TRANSCODER-HP
    7. 24666
    Prev
    Next
    INDEX
    Explanations

    Generic web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AppBundle
    -0.28
    scope
    -0.27
    åĪĨ管
    -0.27
    ourage
    -0.26
    cis
    -0.25
    rys
    -0.25
    ç¾İåªĴ
    -0.25
    zos
    -0.25
    FileVersion
    -0.24
    æĸ°æµª
    -0.24
    POSITIVE LOGITS
     downloadable
    0.32
     interact
    0.30
    åħįè´¹
    0.28
    åĽŀäºĭ
    0.26
    validators
    0.26
    çŃīå¤ļç§į
    0.26
    лоÑģÑĮ
    0.25
    çݩ游æĪı
    0.25
     explanations
    0.25
    æľīå¾Īå¤ļç§į
    0.24
    Activations Density 0.009%

    No Known Activations