© 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. 27874
    Prev
    Next
    INDEX
    Explanations

    kind of / in a way

    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
    unan
    -0.08
    ç²¾ç¥ŀæĸĩæĺİ
    -0.08
    uke
    -0.08
    åŁŃ
    -0.08
     duy
    -0.07
    循çݯç»ıæµİ
    -0.07
    æ£ĭ
    -0.07
    stri
    -0.07
    jin
    -0.07
    æĬij
    -0.07
    POSITIVE LOGITS
    çļĦéĤ£ç§į
    0.11
    éĤ£ç§į
    0.11
    夥
    0.10
    åıĮåIJij
    0.09
    没æľīæĥ³åĪ°
    0.09
    åĮºåŁŁæĢ§
    0.09
    ä¼Ļ
    0.09
    åıijåŀĭ
    0.09
    æĬ¥æ¡Ī
    0.09
    ä»İæł¹æľ¬ä¸Ĭ
    0.09
    Activations Density 0.070%

    No Known Activations