© 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. 20-TRANSCODER-HP
    7. 130316
    Prev
    Next
    INDEX
    Explanations

    unpublished/understudied works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISTRATION
    -0.28
    intel
    -0.27
    ington
    -0.26
    æĺ¨æĻļ
    -0.26
     impres
    -0.25
    imps
    -0.25
    ublisher
    -0.24
     Bá»Ļ
    -0.24
     SetProperty
    -0.24
     intel
    -0.24
    POSITIVE LOGITS
    æĭīæĸ¯
    0.25
    isspace
    0.25
    亲è¿ij
    0.25
    æ§İ
    0.25
    emann
    0.24
    ç§ijæĬĢåĪĽæĸ°
    0.24
     tract
    0.24
    éŀį
    0.23
    ars
    0.23
    PageIndex
    0.23
    Activations Density 10.771%

    No Known Activations