© 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. 50422
    Prev
    Next
    INDEX
    Explanations

    watch Live Streaming

    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
    è°IJ
    -0.09
    çľĭä¸Ĭåİ»
    -0.08
    edException
    -0.08
    ä¼łéĹ»
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    ðŁĴ¯
    -0.08
    _HIDE
    -0.08
    OLS
    -0.08
    ApiController
    -0.07
    çļĦå£°éŁ³
    -0.07
    POSITIVE LOGITS
    çĥŃéĹ¹
    0.11
    /watch
    0.11
     closely
    0.10
    ระว
    0.09
    å¯ĨåĪĩ
    0.09
    è¿Ļä¸ĢåĪĩ
    0.09
    æĪIJéķ¿ä¸º
    0.09
    åĪ«äºº
    0.09
    amy
    0.09
    èĤ¢
    0.09
    Activations Density 0.043%

    No Known Activations