© 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. 58778
    Prev
    Next
    INDEX
    Explanations

    AC/DC conversion or motor

    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
    ç±į
    -0.10
    ocrat
    -0.10
    alist
    -0.09
    rez
    -0.09
    èĬ
    -0.09
    tok
    -0.08
    archical
    -0.08
    ered
    -0.08
    itch
    -0.08
    AIM
    -0.08
    POSITIVE LOGITS
    涵
    0.09
    ä¸į管æĺ¯
    0.09
    襲
    0.09
    éŀį
    0.09
    è¯ĭ
    0.09
    ç¯
    0.09
    _except
    0.09
    æģIJæĢķ
    0.09
    çĶŃ
    0.09
    ervo
    0.08
    Activations Density 0.066%

    No Known Activations