© 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. 26777
    Prev
    Next
    INDEX
    Explanations

    dance and movement arts

    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
    åŁŃ
    -0.09
    ç«ĭå¿Ĺ
    -0.08
    çĬ¹
    -0.08
    天æīį
    -0.08
    thead
    -0.08
     fizz
    -0.08
    _EXTERNAL
    -0.08
    arl
    -0.08
    éľ²å¤©
    -0.08
     Vil
    -0.08
    POSITIVE LOGITS
    èĪŀè¹Ī
    0.17
    è·³èĪŀ
    0.13
    èĪŀ
    0.13
    çļĦåĬ¨ä½ľ
    0.11
    åĬ¨ä½ľ
    0.11
     dancing
    0.11
     dancer
    0.10
     dance
    0.10
    æŃ¦æľ¯
    0.10
    太æŀģæĭ³
    0.10
    Activations Density 0.094%

    No Known Activations