© 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. 17548
    Prev
    Next
    INDEX
    Explanations

    searching through

    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
    æ¯Ķåĸ»
    -0.10
    横
    -0.10
    /gpl
    -0.09
    éĿ¢ç²ī
    -0.09
    .FileReader
    -0.09
    rieb
    -0.09
    ваÑĤ
    -0.09
    urnished
    -0.09
    æĴŃ
    -0.09
    æ´®
    -0.09
    POSITIVE LOGITS
    è¿ijçĻ¾
    0.08
    ä¸ĢåłĨ
    0.08
    å¾Īå¿«å°±
    0.08
    æĹĹå¸ľ
    0.08
    大佬
    0.08
    ä¸ĢäºĽ
    0.08
    ä¸Ģåįĥ
    0.08
    èĪ·
    0.08
    imei
    0.08
    æĭ©
    0.07
    Activations Density 0.018%

    No Known Activations