© 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. 57010
    Prev
    Next
    INDEX
    Explanations

    small intestine/bowel

    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
    å¸Ĥ级
    -0.09
    neau
    -0.09
    å©Ĩ
    -0.09
    伦
    -0.08
    continental
    -0.08
    æĺ¯åĽ½åĨħ
    -0.08
    磶
    -0.08
    MAS
    -0.08
    èĤ¡æĿĥ
    -0.08
    emd
    -0.08
    POSITIVE LOGITS
    ä»ĵ
    0.11
    缴éĶĢ
    0.11
     Äijấu
    0.09
    ault
    0.09
    èĤ®
    0.09
    袢
    0.09
     Trey
    0.09
    ä¸įåľ¨
    0.08
    -dist
    0.08
    缴æİ¥
    0.08
    Activations Density 0.352%

    No Known Activations