© 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. 48791
    Prev
    Next
    INDEX
    Explanations

    film and TV actor roles

    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
     занима
    -0.09
    ढ
    -0.09
     каж
    -0.09
    伫
    -0.09
    dess
    -0.09
    åľ¨å¤ĸéĿ¢
    -0.09
    æºIJæ³ī
    -0.09
    ç¥ŀå·ŀ
    -0.09
    iesen
    -0.09
    изма
    -0.09
    POSITIVE LOGITS
    æĭħä»»
    0.09
    æ´»è·ĥ
    0.08
     roles
    0.08
    æī©
    0.08
    æĢ»æĬķèµĦ
    0.08
    æIJŃ建
    0.08
    ast
    0.07
    èģĺ
    0.07
    æ´»åĬ¨ä¸Ń
    0.07
    çĨŁ
    0.07
    Activations Density 0.137%

    No Known Activations