© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20285
    Prev
    Next
    INDEX
    Explanations

    masturbation

    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
    æ·±åĪ»çļĦ
    -0.09
    æ¦Ĥ
    -0.09
    unce
    -0.08
    çļĦä¸ľè¥¿
    -0.08
    èĩªèº«çļĦ
    -0.08
    çļĦæ¯ĶèµĽ
    -0.08
    oze
    -0.08
    ç«ŀèµĽ
    -0.08
    ised
    -0.07
    æ°ijéĹ´
    -0.07
    POSITIVE LOGITS
    etty
    0.11
    plex
    0.10
    è¡ĵ
    0.10
    èĢħ
    0.10
    æľºä¼ļ
    0.09
     Bucc
    0.09
    èĢħçļĦ
    0.09
    æĪŁ
    0.08
    pping
    0.08
    دÙĤ
    0.08
    Activations Density 0.054%

    No Known Activations