© 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. 17064
    Prev
    Next
    INDEX
    Explanations

    starting in

    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
    erv
    -0.10
    éģ½
    -0.10
    涡
    -0.09
    æĸ«
    -0.09
    BUFF
    -0.08
    ince
    -0.08
    ervo
    -0.08
    RIX
    -0.08
     Coupons
    -0.08
    æĸ°æĹ¶ä»£
    -0.08
    POSITIVE LOGITS
    ä¸įè¦ģ太
    0.10
    unta
    0.10
    isson
    0.09
     пÑĢидеÑĤÑģÑı
    0.09
    ä½Ī
    0.09
    第ä¸ī个
    0.09
    é¢ĨåŁŁçļĦ
    0.09
    çݯèĬĤ
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    第äºĮ个
    0.08
    Activations Density 0.019%

    No Known Activations