© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22325
    Prev
    Next
    INDEX
    Explanations

    by followed by verbs or nouns

    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
    ä¿¡ç®±
    -0.09
    ä¸į该
    -0.09
    è¿ĻéĩĮæľī
    -0.09
    sched
    -0.09
    бан
    -0.08
    BitFields
    -0.08
    æĹ¥ä¸ĭåįĪ
    -0.08
    è¿ĻéĩĮæĺ¯
    -0.08
    .boost
    -0.08
    ä¹ĭç¾İ
    -0.08
    POSITIVE LOGITS
     Hog
    0.09
    caster
    0.09
    rou
    0.09
    å¿ĥæĥ³
    0.09
    æŁ¬
    0.08
    и
    0.08
    éĢĤå½ĵçļĦ
    0.08
    éĵĽ
    0.08
    athing
    0.08
    ä¸¥æł¼çļĦ
    0.08
    Activations Density 0.204%

    No Known Activations