© 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. 63927
    Prev
    Next
    INDEX
    Explanations

    Quotes and excerpts

    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
    ulo
    -0.29
    yn
    -0.27
    onus
    -0.26
    etc
    -0.26
     pres
    -0.25
    Q
    -0.24
    ynn
    -0.24
    yny
    -0.24
    ean
    -0.23
    vd
    -0.23
    POSITIVE LOGITS
    å¼Ģå¿ĥ
    0.27
    utow
    0.26
    mans
    0.26
    iring
    0.26
    ä¸įçŁ¥ä¸į
    0.25
    PELL
    0.24
    llx
    0.23
     dáºŃy
    0.23
    æĭīå¼Ģ
    0.23
    ãĥļ
    0.23
    Activations Density 19.181%

    No Known Activations