© 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. 58047
    Prev
    Next
    INDEX
    Explanations

    much / greatly appreciated

    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
    ç¾ŀ
    -0.11
    åĽłä¸ºä½ł
    -0.10
    ä¸İä¸ŃåĽ½
    -0.09
    åİŁåĽłæĺ¯
    -0.09
    éĽ¾
    -0.09
    çĹ´
    -0.09
    æĸŃ
    -0.09
    æ¹Ľ
    -0.09
    è·Łä½ł
    -0.09
    wig
    -0.09
    POSITIVE LOGITS
    åıĹ欢è¿İ
    0.14
     welcome
    0.13
    欢è¿İ
    0.11
    欢è¿İæĤ¨
    0.11
     welcomed
    0.10
     Welcome
    0.10
    渴
    0.10
    welcome
    0.10
    Welcome
    0.09
    _mgr
    0.09
    Activations Density 0.081%

    No Known Activations