© 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. 2679
    Prev
    Next
    INDEX
    Explanations

    The president

    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¸įä¿¡
    -0.11
    çĦ¶èĢĮ
    -0.10
    åľ°çIJĥä¸Ĭ
    -0.10
    æĤ¨çļĦåŃ©åŃIJ
    -0.10
    ULO
    -0.10
    èĢĮéĿŀ
    -0.09
    å¿«æĿ¥
    -0.09
    èĢĮå·²
    -0.09
    女æĺŁ
    -0.09
    éķ¿å¤§äºĨ
    -0.09
    POSITIVE LOGITS
    æĪijè§īå¾Ĺ
    0.09
    æģIJæħĮ
    0.09
    æĪij个人
    0.08
    åı¯åĪĨ为
    0.08
    arme
    0.08
    Uuid
    0.08
    åĿİåĿ·
    0.07
    _ary
    0.07
    åĪ»èĭ¦
    0.07
    ç»ĻæĪij
    0.07
    Activations Density 0.027%

    No Known Activations