© 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. 22740
    Prev
    Next
    INDEX
    Explanations

    non-medical categories

    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
    æĢ»çĽij
    -0.11
    森æŀĹåħ¬åĽŃ
    -0.11
    ä¸į说
    -0.10
    ä¸İä¸ŃåĽ½
    -0.10
    å¡į
    -0.10
    çī¹åĪ«å£°æĺİ
    -0.10
    æĹ¢æľī
    -0.09
    年纪
    -0.09
    åıijæĮ¥ä½ľçĶ¨
    -0.09
    lettes
    -0.09
    POSITIVE LOGITS
    -centric
    0.09
    -turned
    0.08
     counterparts
    0.08
    åıĻäºĭ
    0.08
    æĢĿç»´
    0.08
    çĶŁæ´»ä¸Ń
    0.07
    çĻ¾å§ĵ
    0.07
    æĥ´
    0.07
    gaben
    0.07
     trom
    0.07
    Activations Density 0.327%

    No Known Activations