© 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. 38925
    Prev
    Next
    INDEX
    Explanations

    medical conditions and symptoms

    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
     Boris
    -0.09
    _HOUR
    -0.09
    :both
    -0.09
    çºł
    -0.08
    鼷éĶĭ
    -0.08
     remed
    -0.08
    ohan
    -0.08
    .currentTime
    -0.08
    éĺ²å¾¡
    -0.08
     Sob
    -0.08
    POSITIVE LOGITS
    è¾Ĺ转
    0.11
    èİ«åIJį
    0.11
    èİ«åIJįåħ¶å¦Ļ
    0.10
    è¿°èģĮ
    0.10
    躬
    0.10
    è¿·æĥij
    0.09
    éº»æľ¨
    0.09
    çīĻ
    0.09
    æļ§
    0.08
    é¹ĥ
    0.08
    Activations Density 0.308%

    No Known Activations