© 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. 63163
    Prev
    Next
    INDEX
    Explanations

    from date and after

    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
    åı¦ä¸ĢåįĬ
    -0.10
    çijŁ
    -0.10
     СÑĤа
    -0.09
    ä¸Ńåľº
    -0.09
    åĬĪ
    -0.09
    è¿ĻäºĽå¹´
    -0.09
    åĿŁ
    -0.09
    è¡Ķ
    -0.09
    çŀŃ
    -0.08
    çļĦåIJĦ项
    -0.08
    POSITIVE LOGITS
     заÑĢегиÑģÑĤ
    0.09
     мом
    0.08
     day
    0.08
    .gg
    0.08
     Maul
    0.08
     Kauf
    0.08
    éĢ®
    0.08
     dual
    0.08
    zeit
    0.08
    .del
    0.08
    Activations Density 0.020%

    No Known Activations