© 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. 18464
    Prev
    Next
    INDEX
    Explanations

    use the

    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
    åĿıäºĨ
    -0.10
    imeo
    -0.10
    çŁ¥éģĵèĩªå·±
    -0.09
    ç¹ģå¿Ļ
    -0.09
    ä¸Ńåľº
    -0.09
    è¿ĺæľīä¸Ģ个
    -0.09
    agento
    -0.09
     Kushner
    -0.09
    åįĬ个
    -0.09
    ä¸įè¦ģåĨį
    -0.09
    POSITIVE LOGITS
     liken
    0.08
     UPC
    0.08
    .mount
    0.08
    oring
    0.08
    .or
    0.08
    æĸĩåŃĹ
    0.07
    newline
    0.07
    å¯Ĵ
    0.07
    _GO
    0.07
    è¿Ł
    0.07
    Activations Density 0.028%

    No Known Activations