© 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. 5100
    Prev
    Next
    INDEX
    Explanations

    as, because

    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
    обÑĭ
    -0.11
    å½·
    -0.10
    鸢
    -0.09
    å¾¼
    -0.09
    ç¿ķ
    -0.09
    è°İè¨Ģ
    -0.09
    å¢ŀè¿Ľ
    -0.09
    éĵ³
    -0.09
    ç»ĦåĽ¾
    -0.09
    çĵ®
    -0.09
    POSITIVE LOGITS
    ä¸įå¾Ĺä¸į说
    0.11
    eros
    0.10
    ä¸įå¾Ĺä¸į
    0.09
     <![
    0.09
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.08
    пад
    0.08
    çIJIJ
    0.08
    omp
    0.08
    ersen
    0.08
    receipt
    0.08
    Activations Density 0.023%

    No Known Activations