© 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. 34096
    Prev
    Next
    INDEX
    Explanations

    comycin, vancomycin

    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
    空
    -0.11
    ä¼´
    -0.10
    ç²¾èĭ±
    -0.09
    _lite
    -0.09
    forcer
    -0.08
    برا
    -0.08
    æĿ¯åŃIJ
    -0.08
    INF
    -0.08
    mente
    -0.08
    MENT
    -0.08
    POSITIVE LOGITS
    æĦ§
    0.09
    è°ĭ
    0.09
    licative
    0.08
    çķĻ
    0.08
    éģŃ
    0.08
     avent
    0.08
    æĿĥ
    0.08
    æĺ¯çĶ¨æĿ¥
    0.08
    çģ
    0.08
    åĴĢ
    0.08
    Activations Density 0.060%

    No Known Activations