© 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. 23186
    Prev
    Next
    INDEX
    Explanations

    insects that bite or cause nuisance

    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
    è°İ
    -0.09
    leen
    -0.09
    丸
    -0.08
    åİ¥
    -0.08
     Pasta
    -0.08
    æ®ī
    -0.08
    å¯Ĵåģĩ
    -0.08
    ç§ĺå¯Ĩ
    -0.08
     trans
    -0.08
    çĥĺ
    -0.08
    POSITIVE LOGITS
    èļĬ
    0.15
     mosquito
    0.14
    åı®
    0.13
    æĮ½
    0.10
     mosquitoes
    0.10
    æĹ¥æĻļéĹ´
    0.09
    èĺ§
    0.09
    èĦij
    0.09
    éĺ²èĮĥ
    0.09
    海滨
    0.09
    Activations Density 0.107%

    No Known Activations