© 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. 108302
    Prev
    Next
    INDEX
    Explanations

    Quotations

    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
    GES
    -0.25
    nier
    -0.24
    rier
    -0.24
    stile
    -0.24
    å£ij
    -0.24
     wh
    -0.24
    -wh
    -0.24
     Tier
    -0.23
    zip
    -0.23
     rev
    -0.23
    POSITIVE LOGITS
    ç½ijåıĭ
    0.33
     blog
    0.31
    æľ¬ç½ij
    0.30
    æĸ°éĹ»ç½ij
    0.30
    ç½ij
    0.29
    blog
    0.28
    Blog
    0.26
    ç½ij讯
    0.26
    ieber
    0.26
    CEPT
    0.25
    Activations Density 21.924%

    No Known Activations