© 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. 32563
    Prev
    Next
    INDEX
    Explanations

    Boko Haram, Sultan, Del

    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
    çªģçł´åı£
    -0.09
     Ne
    -0.09
     Conte
    -0.09
    iro
    -0.09
     TEX
    -0.09
    èĩªçĦ¶ä¿ĿæĬ¤
    -0.08
    å¾·å·ŀ
    -0.08
    èĽ®
    -0.08
    ç¨ļ
    -0.08
    å¼ıçļĦ
    -0.08
    POSITIVE LOGITS
    ishi
    0.10
    ittings
    0.10
    å²±
    0.09
    å¼ĢåºĹ
    0.09
    aku
    0.09
    CreatedBy
    0.09
    èķ¤
    0.08
    ä¸ĢåľĪ
    0.08
    ç³Ĭæ¶Ĥ
    0.08
    .Serial
    0.08
    Activations Density 0.120%

    No Known Activations