© 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. 5444
    Prev
    Next
    INDEX
    Explanations

    wash or hygiene

    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
    scribe
    -0.10
    åĬª
    -0.10
    çIJ´
    -0.09
    è¯Ħè®®
    -0.09
    æ¥
    -0.08
    ToList
    -0.08
    é¹Ĭ
    -0.08
    èĢĴ
    -0.08
    弩
    -0.08
    è·Ľ
    -0.08
    POSITIVE LOGITS
    åĬŁè¯¾
    0.10
    è¿ĻåĿĹ
    0.10
    缸è¿ij
    0.10
    æİĪ课
    0.09
    ouri
    0.09
     advent
    0.09
    è¿Ŀ纪
    0.09
     lent
    0.08
    æģŃ
    0.08
    Õ¼
    0.08
    Activations Density 0.019%

    No Known Activations