© 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. 23362
    Prev
    Next
    INDEX
    Explanations

    only option

    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
    ä¸Ģç³»åĪĹ
    -0.13
    ä¸įåĩĨ
    -0.10
    ä¸ļåĨħ
    -0.09
    æľ¬èº«å°±
    -0.09
    çļĦä¸Ģ大
    -0.08
    æľīå¾Īå¤ļç§į
    -0.08
    stud
    -0.08
    大åħ¨
    -0.08
    大éĻĨ
    -0.08
    Stra
    -0.08
    POSITIVE LOGITS
     thing
    0.11
    æĭħå¿ĥ
    0.10
    羣æŃ£
    0.10
     reason
    0.10
     truly
    0.10
    thing
    0.09
    åİŁåĽłæĺ¯
    0.09
    tol
    0.09
    æļ¨
    0.09
    tó
    0.09
    Activations Density 0.013%

    No Known Activations