© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7402
    Prev
    Next
    INDEX
    Explanations

    olly, ally, Polly, helium

    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
     Commons
    -0.10
    erring
    -0.09
    à¸Ļาà¸Ļ
    -0.09
    ially
    -0.09
    errupt
    -0.09
    hel
    -0.09
    æİī
    -0.08
    illis
    -0.08
    icular
    -0.08
    rome
    -0.08
    POSITIVE LOGITS
    brew
    0.10
     ведÑĮ
    0.09
    oho
    0.09
    ìį¨
    0.09
    ä¸įéĶĻ
    0.09
    boy
    0.09
    ously
    0.09
    èµ·æĿ¥
    0.09
    æĥ¬æĦı
    0.09
    ibri
    0.08
    Activations Density 0.003%

    No Known Activations