© 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. 23947
    Prev
    Next
    INDEX
    Explanations

    film or movie descriptions

    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
    æľªå¿ħ
    -0.09
    声åĵį
    -0.08
    å¥ĸ
    -0.08
    ç»Ĵ
    -0.08
    å·¥ä½ľå²Ĺä½į
    -0.08
    æĬĹè®®
    -0.08
    ä½ľåĿĬ
    -0.08
    鼷æĸ¯
    -0.08
    æĸĻ
    -0.08
    éĤ£æ¬¡
    -0.08
    POSITIVE LOGITS
    ä¸İåħ¶
    0.10
    ixon
    0.10
    -going
    0.09
    è¹Ĭ
    0.09
     sided
    0.09
    ILES
    0.09
    è¡¡
    0.09
    èĬĻèĵī
    0.08
    ä¸ŃçļĦ
    0.08
    大åݦ
    0.08
    Activations Density 0.090%

    No Known Activations