© 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. 31400
    Prev
    Next
    INDEX
    Explanations

    Irvine, University names, Eaton thinks

    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
    ì¹Ń
    -0.10
    ubs
    -0.09
    举æĸ¹
    -0.09
    _ACCEPT
    -0.09
    ä¸Ģç¢Ĺ
    -0.09
    ä¸ĵåįĸåºĹ
    -0.08
    彪
    -0.08
    é£ı
    -0.08
    èĻ¾
    -0.08
    èģª
    -0.08
    POSITIVE LOGITS
    ç¼Ħ
    0.09
    able
    0.09
    å°¾
    0.09
    orro
    0.08
    åѤåĦ¿
    0.08
     Saskatchewan
    0.08
    æŃ£æĺ¯
    0.08
    ï¸ı
    0.08
    æĴ¬
    0.08
    earch
    0.08
    Activations Density 0.003%

    No Known Activations