© 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. 11740
    Prev
    Next
    INDEX
    Explanations

    animal welfare

    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
    æįı
    -0.09
    æĬĬèĩªå·±
    -0.09
    è·ª
    -0.09
     Wake
    -0.09
    lane
    -0.08
    çݯå¢ĥ污æŁĵ
    -0.08
    çįĴ
    -0.08
    å°Ĩèĩªå·±çļĦ
    -0.08
     RSVP
    -0.08
    embre
    -0.08
    POSITIVE LOGITS
    åIJł
    0.10
    styled
    0.10
    æļ´é£İ
    0.09
    èĭ±æīį
    0.09
    .interpolate
    0.09
     пÑĢим
    0.09
    çĮĹ
    0.09
    htable
    0.09
     taraf
    0.09
    æĸ¹éĿ¢çļĦ
    0.09
    Activations Density 0.019%

    No Known Activations