© 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. 18467
    Prev
    Next
    INDEX
    Explanations

    get into

    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
    éĺ¿æ£®
    -0.11
    å³Ļ
    -0.09
    à¸IJ
    -0.09
    alte
    -0.09
    akens
    -0.09
    ingly
    -0.08
    riba
    -0.08
    ç²īèī²
    -0.08
    кеÑĢ
    -0.08
    æĪijåĸľæ¬¢
    -0.08
    POSITIVE LOGITS
    æİī
    0.08
     bi
    0.08
     elt
    0.08
     ÐĴлад
    0.08
    dera
    0.08
     NotImplemented
    0.08
    éĥ
    0.08
    çĭIJ
    0.08
    intr
    0.08
    å§IJ
    0.08
    Activations Density 0.056%

    No Known Activations