© 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. 141043
    Prev
    Next
    INDEX
    Explanations

    Charity/Philanthropy

    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
     Äijiá»ĥn
    -0.26
    æĤ´
    -0.24
    åĦ¿
    -0.24
     rep
    -0.23
    ods
    -0.23
    xing
    -0.23
    umat
    -0.23
    åĶ³
    -0.23
    resolver
    -0.23
    éļĽãģ«
    -0.23
    POSITIVE LOGITS
    weep
    0.31
    ç®Ĺ
    0.28
    èµĽ
    0.26
    wich
    0.25
    tte
    0.25
     Scho
    0.25
    lymp
    0.23
     dra
    0.23
     isNaN
    0.23
    貫
    0.22
    Activations Density 4.994%

    No Known Activations