© 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. 26393
    Prev
    Next
    INDEX
    Explanations

    doing things

    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
     bool
    -0.08
    .boolean
    -0.08
    REEN
    -0.08
    åıĪ称
    -0.08
    ä¸İåIJ¦
    -0.08
    MY
    -0.08
    èħķ
    -0.08
     Blonde
    -0.08
     Bro
    -0.08
    .bool
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.11
    è¿ĻäºĽä¸ľè¥¿
    0.10
    åģļåĪ°äºĨ
    0.09
    ä½ıæīĢ
    0.09
    éĢĨè¡Į
    0.09
    æĸ¥
    0.09
    æİīäºĨ
    0.09
    ç¬ĶèĢħ
    0.09
    æ½ľ
    0.09
    è¿Ļä¸ĢåĪĩ
    0.09
    Activations Density 0.174%

    No Known Activations