© 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. 63549
    Prev
    Next
    INDEX
    Explanations

    facial expressions and reactions

    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
    ACHI
    -0.10
    羿
    -0.09
    tle
    -0.09
    è¦ģçĤ¹
    -0.09
    åħ¥æīĭ
    -0.09
    æįĨ
    -0.09
    éĶī
    -0.08
    achi
    -0.08
    uron
    -0.08
    桧
    -0.08
    POSITIVE LOGITS
    表æĥħ
    0.13
    姿æĢģ
    0.11
    姿åĬ¿
    0.10
    çľī
    0.10
    êµ´
    0.10
    çļĦ表æĥħ
    0.10
    æĦģ
    0.10
    åĬ¨ä½ľ
    0.09
     emot
    0.09
    (sk
    0.09
    Activations Density 0.042%

    No Known Activations