© 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. 38416
    Prev
    Next
    INDEX
    Explanations

    quiz, test, question

    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
    ç»ıå¼Ģ
    -0.10
    utilus
    -0.10
    ä¸įèī¯ä¿¡æģ¯
    -0.10
    åĴĨ
    -0.09
     اÙĦØ£ÙĪ
    -0.09
     Specifications
    -0.09
    à§İ
    -0.09
    åıijå¸ĥåħ¬åijĬ
    -0.09
    edList
    -0.08
    annis
    -0.08
    POSITIVE LOGITS
    èĩªæĪij
    0.12
    æµĭè¯ķ
    0.11
    å¾ĹäºĨ
    0.10
    让èĩªå·±
    0.10
     test
    0.10
    åħ¬æŃ£
    0.09
     Ow
    0.09
    test
    0.09
    è¯Ħä¼°
    0.09
    self
    0.09
    Activations Density 0.073%

    No Known Activations