© 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. 30134
    Prev
    Next
    INDEX
    Explanations

    recommending actions or items

    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
    åī¯æĢ»
    -0.10
    足迹
    -0.09
    åĬĽè¿ĺæĺ¯
    -0.09
    æ¶Ī
    -0.09
    oup
    -0.09
    ä»ĩ
    -0.09
     SAFE
    -0.08
    彬
    -0.08
    ä¸įæĦ¿æĦı
    -0.08
    ä»Ģä¹Īä¸ľè¥¿
    -0.08
    POSITIVE LOGITS
    æŀľæĸŃ
    0.10
    æĴº
    0.09
    赶紧
    0.09
    å°ĨæĿ¥
    0.09
    ç»Ŀ对æĺ¯
    0.09
    åĬłå¼ºå¯¹
    0.09
    oce
    0.09
    åı¦ä¸ĢåįĬ
    0.09
    çģµæķı
    0.09
    尽快
    0.09
    Activations Density 0.073%

    No Known Activations