© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50142
    Prev
    Next
    INDEX
    Explanations

    convert to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ¨éķ¿
    -0.08
    uned
    -0.08
    ref
    -0.08
    纵横
    -0.08
    ned
    -0.08
    åĪĨè¡Į
    -0.08
    ãģªãģĦãĤĪãģĨãģ«
    -0.08
    nz
    -0.08
    awan
    -0.08
    .paging
    -0.08
    POSITIVE LOGITS
    转æį¢
    0.13
     Converter
    0.11
    转åĮĸ
    0.10
    å·´å·´
    0.10
     Conversion
    0.09
    .Convert
    0.09
     convert
    0.09
     converting
    0.09
    converter
    0.09
     conversion
    0.09
    Activations Density 0.165%

    No Known Activations