© 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. 37953
    Prev
    Next
    INDEX
    Explanations

    end of something

    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
    ä¸įä»ħåı¯ä»¥
    -0.09
    è¯ŀçĶŁ
    -0.09
    kie
    -0.09
    å¿į
    -0.09
     вÑĭп
    -0.09
    çİ°è¡Į
    -0.09
     Sight
    -0.08
    éĻī
    -0.08
    .curr
    -0.08
    ä¸ĭä¸ĢæŃ¥
    -0.08
    POSITIVE LOGITS
    åĩłæ¬¡
    0.13
    åIJİæľŁ
    0.13
    åĪ°æľĢåIJİ
    0.11
    贯穿
    0.10
    é¢ijç¹ģ
    0.10
     later
    0.09
    第ä¸ī个
    0.09
    åIJİéĿ¢çļĦ
    0.09
    转æĬĺ
    0.09
    åIJİæĿ¥
    0.08
    Activations Density 0.106%

    No Known Activations