© 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. 130036
    Prev
    Next
    INDEX
    Explanations

    code or technical documents

    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
    æĹłåģ¿
    -0.27
     sơ
    -0.27
    åŀĴ
    -0.27
    å¾Ļ
    -0.25
    æ¯ĶåĪĨ
    -0.25
    ä¸įåĬ¨
    -0.25
     giveaways
    -0.25
    vature
    -0.25
    leness
    -0.23
    ç¬ijèĦ¸
    -0.23
    POSITIVE LOGITS
    ñana
    0.29
    以为
    0.27
    ensed
    0.26
    prite
    0.26
     subjects
    0.25
     "../../../../
    0.24
    eced
    0.24
    verages
    0.24
    ensing
    0.24
    Sus
    0.24
    Activations Density 6.522%

    No Known Activations