© 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. 10097
    Prev
    Next
    INDEX
    Explanations

    confidence, knowledge, hope, authority

    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
    æĪijä¼ļ
    -0.08
    æĪij个人
    -0.07
    åĸī
    -0.07
    2
    -0.07
     scares
    -0.07
    ç»ĻäºĨæĪij
    -0.07
    妥åįı
    -0.07
    æħ¢æħ¢çļĦ
    -0.07
    éļĽ
    -0.07
    使æĪij
    -0.07
    POSITIVE LOGITS
    侮辱
    0.10
    åħ¨éĿ¢å»ºæĪIJ
    0.09
    ç»Łæ²»
    0.09
    æ¯ķç«Łæĺ¯
    0.09
    _FS
    0.08
    æ¯Ķäºļ
    0.08
    éĥijéĩį
    0.08
    æĹłå¿§
    0.08
    æĬĹæĪĺ
    0.08
    æŁ¥çľĭåħ¨æĸĩ
    0.08
    Activations Density 0.042%

    No Known Activations