© 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. 57664
    Prev
    Next
    INDEX
    Explanations

    people told someone

    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
    è¿Ł
    -0.11
    éĢģæĿ¥
    -0.10
    ç¼£
    -0.09
    éģ²
    -0.09
    æĪ¶
    -0.09
    羣çļ®
    -0.09
    涣
    -0.09
    é¢ijé¢ij
    -0.09
    è¿Łè¿Ł
    -0.09
    åŃĹ
    -0.09
    POSITIVE LOGITS
    è°ģçŁ¥éģĵ
    0.16
    å°ijæķ°
    0.11
    没人
    0.10
    è°ģçŁ¥
    0.10
    没æľī人
    0.10
    åĩłä¸ªäºº
    0.10
    åıªæľī
    0.10
    æĹłäºº
    0.09
    ä¾ĭå¤ĸ
    0.09
    èµı
    0.09
    Activations Density 0.060%

    No Known Activations