© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60583
    Prev
    Next
    INDEX
    Explanations

    game names (Tic-Tac-Toe, Heads and Tails)

    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
    Negative Logits
    空éĹ´
    -0.09
     ÑģбоÑĢ
    -0.09
    idend
    -0.09
    积æ·Ģ
    -0.09
    éĶĢ
    -0.09
    è¡ĢèĦī
    -0.08
    éĺµåľ°
    -0.08
    çļĦ空éĹ´
    -0.08
    è·ijäºĨ
    -0.08
    éĻĮçĶŁ
    -0.08
    POSITIVE LOGITS
    -fw
    0.10
    åħļå·¥å§Ķ
    0.10
    UDO
    0.08
    çķĮçļĦ
    0.08
    åıijæī¬
    0.08
    æīİæł¹
    0.08
    worth
    0.08
    راس
    0.08
    ç»įåħ´
    0.08
    åĽ¢ä½ĵ
    0.08
    Activations Density 0.008%

    No Known Activations