© 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. 57778
    Prev
    Next
    INDEX
    Explanations

    confidentiality and disclosure

    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
    éĻIJé¢Ŀ
    -0.09
    å½»
    -0.09
    å±ĢéĻIJ
    -0.09
    ä½İæĪIJæľ¬
    -0.08
    erm
    -0.08
    æłİ
    -0.08
    声åĵį
    -0.08
    æĦıæĢĿæĺ¯
    -0.08
    æĬĽ
    -0.08
    æĹĦ
    -0.08
    POSITIVE LOGITS
    ä¿Ŀå¯Ĩ
    0.15
     confidential
    0.13
     Confidential
    0.12
     confidentiality
    0.11
    éļIJç§ģ
    0.10
    çļĦç§ĺå¯Ĩ
    0.09
    ç§ĺå¯Ĩ
    0.09
    éĽª
    0.09
    èľī
    0.09
    æ³Ħéľ²
    0.09
    Activations Density 0.136%

    No Known Activations