© 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. 26367
    Prev
    Next
    INDEX
    Explanations

    names and programming constructs

    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
    haus
    -0.13
    趸
    -0.11
    ç¿»
    -0.10
    æĺĻ
    -0.09
    éĨ®
    -0.09
    abama
    -0.09
    æļĿ
    -0.09
    çļĦçĶ·äºº
    -0.09
    è¿ĻçĤ¹
    -0.09
    è
    -0.09
    POSITIVE LOGITS
    æĢĿ绪
    0.09
     POD
    0.08
     Bott
    0.08
    åŃĿ
    0.08
     Rut
    0.08
     Heb
    0.07
     tow
    0.07
    ovid
    0.07
    oram
    0.07
     instant
    0.07
    Activations Density 0.001%

    No Known Activations