© 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. 3239
    Prev
    Next
    INDEX
    Explanations

    competitions and contests

    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
    Fed
    -0.09
    çķı
    -0.08
    æĦļ
    -0.08
    rial
    -0.08
    еÑģÑĤÑĮ
    -0.08
    ç½¢
    -0.08
    unga
    -0.08
    comed
    -0.08
    为ä¾ĭ
    -0.08
    (pad
    -0.08
    POSITIVE LOGITS
    人æ°Ķ
    0.09
    æľĢåıĹ
    0.09
    OTS
    0.09
    é¹ħ
    0.09
    çļĦ表æĥħ
    0.09
    åĪĽæĸ°èĥ½åĬĽ
    0.09
    åı¯éĿłçļĦ
    0.09
    çijĻ
    0.09
    ä¸Ģç³»åĪĹ
    0.08
    éļ¶å±ŀ
    0.08
    Activations Density 0.086%

    No Known Activations