© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16850
    Prev
    Next
    INDEX
    Explanations

    products and technology

    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
    群éĩĮ
    -0.10
    çļĦéĤ£ç§į
    -0.09
    俯
    -0.09
    å¿ĹæĦ¿èĢħ
    -0.09
    éĤ£ç§į
    -0.09
    å¾ĢæĿ¥
    -0.08
    DEPTH
    -0.08
    à¸ģà¸Ńà¸ĩ
    -0.08
    ä¸ĭè¡Į
    -0.08
    /vendors
    -0.08
    POSITIVE LOGITS
    类产åĵģ
    0.14
    çĶ¨åĵģ
    0.11
     products
    0.10
    产åĵģ
    0.10
    çĻ¾ç§ij
    0.09
    ç³»åĪĹ产åĵģ
    0.09
    çĶŁåij½åij¨æľŁ
    0.09
     bour
    0.09
    娥
    0.08
    åIJijãģij
    0.08
    Activations Density 0.358%

    No Known Activations