© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7318
    Prev
    Next
    INDEX
    Explanations

    "At" followed by "We"

    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
    urge
    -0.10
    mk
    -0.09
    _mk
    -0.09
    FORCE
    -0.08
    shal
    -0.08
    ktion
    -0.08
    usan
    -0.08
    udget
    -0.08
     Bugs
    -0.08
     ÑģÑĤанов
    -0.08
    POSITIVE LOGITS
    èĩ´åĬĽ
    0.13
    客æĪ·æıIJä¾Ľ
    0.10
    æ·±åĪĩ
    0.09
    ä¸įå¿ĺ
    0.09
    æĤ¨çļĦåŃ©åŃIJ
    0.09
    海滨
    0.09
    åħ¨ä½ĵåijĺå·¥
    0.09
    åķ¬
    0.09
    æ·±çŁ¥
    0.09
    èĩ´åĬĽäºİ
    0.08
    Activations Density 0.161%

    No Known Activations