© 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. 49207
    Prev
    Next
    INDEX
    Explanations

    spellings and pronunciations

    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
     Termin
    -0.09
    å±ij
    -0.09
    寸
    -0.09
     Ùħت
    -0.08
    å¥Ĺè·¯
    -0.08
    æĦĪ
    -0.08
    æĿł
    -0.08
    aisal
    -0.08
     termin
    -0.08
    imed
    -0.08
    POSITIVE LOGITS
    å°ijæķ°æ°ijæĹı
    0.11
     spelled
    0.10
     Phon
    0.10
    åıijéŁ³
    0.10
    èĪĴ
    0.10
     phon
    0.09
    éŁ¿
    0.09
    æľ¬æĿ¥å°±
    0.09
    ä¸įå¾Ĺä¸į说
    0.09
    zion
    0.09
    Activations Density 0.080%

    No Known Activations