© 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. 33029
    Prev
    Next
    INDEX
    Explanations

    LICENSE and COPYRIGHT

    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
    تÙĪ
    -0.10
    足
    -0.09
     ÐIJлекÑģан
    -0.09
     bran
    -0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.09
    åĽ°éļ¾
    -0.09
    æĢ»æľī
    -0.08
    满满
    -0.08
    (LOG
    -0.08
    /her
    -0.08
    POSITIVE LOGITS
    /OR
    0.11
    ’S
    0.10
    'S
    0.09
    _CTX
    0.09
    каÑĤ
    0.09
    eming
    0.08
    alyze
    0.08
    ÙĪÙģ
    0.08
    odyn
    0.08
    æīĵæŀ¶
    0.08
    Activations Density 1.250%

    No Known Activations