© 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. 22747
    Prev
    Next
    INDEX
    Explanations

    OW Holster

    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
    stoff
    -0.10
     spo
    -0.10
    èĴ¸
    -0.09
    iday
    -0.09
    æµ´
    -0.09
    æĨİ
    -0.09
     punt
    -0.08
    ost
    -0.08
    TeV
    -0.08
    itzer
    -0.08
    POSITIVE LOGITS
    antine
    0.09
    èįĶæŀĿ
    0.09
    elian
    0.09
    æIJº
    0.08
    èĸ¤
    0.08
    æķ¢
    0.08
    课åłĤæķĻåѦ
    0.08
    (Locale
    0.08
    æĭ¿äºĨ
    0.08
    [...,
    0.08
    Activations Density 0.158%

    No Known Activations