© 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. 2641
    Prev
    Next
    INDEX
    Explanations

    do justice

    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
    mine
    -0.09
    Lady
    -0.08
    追究
    -0.08
    è¨Ģ
    -0.08
     дог
    -0.08
    æľī人
    -0.08
    æİ¢
    -0.08
     Eaton
    -0.08
     Rock
    -0.08
    .patch
    -0.08
    POSITIVE LOGITS
    好å¤Ħ
    0.11
     ÑĥÑģлÑĥги
    0.10
    çļĦåį±å®³
    0.10
    æīĭèĦļ
    0.10
    æľįåĬ¡
    0.10
    è¾Ł
    0.10
    çļĦ好å¤Ħ
    0.09
    åĿİ
    0.09
    人æ°ijæľįåĬ¡
    0.09
     phục
    0.09
    Activations Density 0.040%

    No Known Activations