© 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. 56329
    Prev
    Next
    INDEX
    Explanations

    there is an

    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
    åľ¨éĩĮéĿ¢
    -0.09
    ãģĽãģĦ
    -0.08
    .land
    -0.08
    apy
    -0.08
    åĪijäºĭ责任
    -0.08
    娩
    -0.08
    å¥
    -0.08
    avig
    -0.07
    å¾Ĺä½ı
    -0.07
     Sha
    -0.07
    POSITIVE LOGITS
    è¿ĺæľīä¸Ģ个
    0.13
    æ²»æĦĪ
    0.11
     Fleming
    0.10
    转载请
    0.09
    è¿ĺæĥ³
    0.09
    缮åīįæŃ£åľ¨
    0.09
    æľ¬æ¬¡
    0.09
    æľī两ç§į
    0.09
    TestMethod
    0.09
    ä¸Ĭ游
    0.09
    Activations Density 0.065%

    No Known Activations