© 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. 26437
    Prev
    Next
    INDEX
    Explanations

    no X specified

    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¿ĺæĺ¯è¦ģ
    -0.10
    \↵
    -0.09
    è¿ĺæĺ¯ä¼ļ
    -0.09
    yme
    -0.08
     midd
    -0.08
    è¿ĺæĺ¯å¾Ī
    -0.08
    为主
    -0.08
    aille
    -0.08
    欢è¿İ
    -0.07
    hone
    -0.07
    POSITIVE LOGITS
    dur
    0.10
    ROUGH
    0.10
    è¿Ľå±ķæĥħåĨµ
    0.09
    åĨĢ
    0.09
    被èªī为
    0.08
    ä»»ä½ķ人
    0.08
    类产åĵģ
    0.08
    éļ¶å±ŀäºİ
    0.08
    _OCC
    0.08
    Dur
    0.08
    Activations Density 0.014%

    No Known Activations