© 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. 17514
    Prev
    Next
    INDEX
    Explanations

    hesitation sounds and questions

    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
    nist
    -0.08
    ograd
    -0.08
    éªļ
    -0.07
    大æī¹
    -0.07
    alte
    -0.07
    åģı
    -0.07
    ä¼IJ
    -0.07
    æĥħ
    -0.07
    éľ²å¤©
    -0.07
     Copp
    -0.07
    POSITIVE LOGITS
    ä¸įæ¸ħ
    0.12
    çıij
    0.11
    ç½ij游
    0.10
    çİ©æĦı
    0.10
    çĹĴ
    0.09
    avig
    0.09
    çļĦçľ¼ç¥ŀ
    0.09
    éĴ¹
    0.09
    .localization
    0.09
    ä¸įé«ĺ
    0.09
    Activations Density 0.002%

    No Known Activations