© 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. 21566
    Prev
    Next
    INDEX
    Explanations

    settings and parameters

    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
    è¿Ļéĥ¨åĪĨ
    -0.09
    éŃĤ
    -0.09
    åĽ´ç»ķ
    -0.09
    æݥ触åĪ°
    -0.08
    åĮĸè¿Ľç¨ĭ
    -0.08
     Fried
    -0.08
    à¸Ńà¸Ķ
    -0.08
    jen
    -0.08
    æĽ´å¤ļä¿¡æģ¯
    -0.08
    è¾Ļ
    -0.08
    POSITIVE LOGITS
    æ¡£
    0.12
     settings
    0.11
    æªĶ
    0.10
    太é«ĺ
    0.09
    éĢĤåIJĪèĩªå·±
    0.09
    settings
    0.09
     ÑĢежим
    0.09
    ãģ«ãģĹãģ¦
    0.09
     level
    0.09
     mode
    0.09
    Activations Density 0.077%

    No Known Activations