© 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. 35045
    Prev
    Next
    INDEX
    Explanations

    vestibular or amic endings

    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
    åIJİæİĴ
    -0.09
    衬
    -0.09
    ãģıãĤĮ
    -0.09
    æĺ¯ä¸ºäºĨ
    -0.09
    主è§Ĥ
    -0.09
    é»ijå¤ľ
    -0.08
     há»ĵ
    -0.08
    buster
    -0.08
    TRS
    -0.08
    马路
    -0.08
    POSITIVE LOGITS
    ä¸īåĨľ
    0.09
    æijĩ
    0.09
    è¿ģ
    0.09
    æĻĥ
    0.09
    è¿Ļä¸ĢåĪĩ
    0.08
    aster
    0.08
    å¤§èµĽ
    0.08
    ä¿¡æģ¯æĬ«éľ²
    0.08
    ë¡ł
    0.08
    缮æłĩä»»åĬ¡
    0.08
    Activations Density 0.001%

    No Known Activations