© 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. 55190
    Prev
    Next
    INDEX
    Explanations

    three words or numbers

    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
    .Dialog
    -0.09
    åħ¸åŀĭ
    -0.09
    cases
    -0.09
    æĿijåħļæĶ¯éĥ¨
    -0.09
    åŁ·
    -0.09
    åį³æŶ
    -0.08
    åĪĿ级
    -0.08
    ÙĥاÙħ
    -0.08
    æī§
    -0.08
    æĭľçĻ»
    -0.08
    POSITIVE LOGITS
    缦
    0.09
     наÑĥк
    0.09
    æ¿ł
    0.09
    kid
    0.09
    æ°´ä¸Ń
    0.08
    å±İ
    0.08
    èĭ¦èĭ¦
    0.08
    èĤĿèĦı
    0.08
    æĪijå¿ĥéĩĮ
    0.08
    é¢ĦåijĬ
    0.08
    Activations Density 0.084%

    No Known Activations