© 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. 17926
    Prev
    Next
    INDEX
    Explanations

    League names and teams

    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
    åĨ¶
    -0.09
    _Module
    -0.09
    æĬĴ
    -0.09
    å¸Ĥåľºä¸»ä½ĵ
    -0.09
    æĬĺ
    -0.09
    èĩ£
    -0.09
    anke
    -0.08
    uth
    -0.08
    éĴ¥
    -0.08
    å¸ļ
    -0.08
    POSITIVE LOGITS
     Maher
    0.09
    ç¡®åĪĩ
    0.09
    å¾ģæ±Ĥ
    0.08
    ITE
    0.08
    òng
    0.08
    гÑĢан
    0.08
    ollo
    0.08
    è²Į
    0.08
     clam
    0.08
    éĩĮç¨ĭ
    0.08
    Activations Density 0.003%

    No Known Activations