© 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. 33525
    Prev
    Next
    INDEX
    Explanations

    keywords and terms

    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
    è½®å»ĵ
    -0.09
    åĪijèѦ
    -0.09
    ä¸įå¼Ģ
    -0.09
    è¹Ĵ
    -0.09
    è¶ħè¿ĩ
    -0.09
    人社
    -0.09
    ç«ĻçĿĢ
    -0.09
    ÙģصÙĦ
    -0.09
    æĪĴ
    -0.09
    ä¸Ģç«Ļ
    -0.08
    POSITIVE LOGITS
    åħ³éĶ®è¯į
    0.16
     keywords
    0.16
     words
    0.14
    Keywords
    0.14
    keywords
    0.13
    åħ³éĶ®åŃĹ
    0.12
     Keywords
    0.12
     keyword
    0.12
    .Keyword
    0.12
    è¯į
    0.11
    Activations Density 0.096%

    No Known Activations