© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20879
    Prev
    Next
    INDEX
    Explanations

    specific reason or order

    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
    æŃ»è§Ĵ
    -0.09
    zie
    -0.08
     lẽ
    -0.08
    екÑģ
    -0.08
    lem
    -0.08
    认
    -0.08
    zf
    -0.08
     secrets
    -0.08
    çļ±
    -0.08
    å·®ä¸įå¤ļ
    -0.08
    POSITIVE LOGITS
    æĦŁåħ´è¶£çļĦ
    0.10
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    0.09
    enden
    0.09
    æŀľ
    0.09
    oba
    0.09
    иÑģÑĤ
    0.09
    æĦŁåħ´è¶£
    0.09
    diet
    0.08
     Chat
    0.08
    ç¡®å®ŀ
    0.08
    Activations Density 0.015%

    No Known Activations