© 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. 56976
    Prev
    Next
    INDEX
    Explanations

    time intervals

    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
    åĩłå¤©
    -0.11
    ä¸Ģ段æŶéĹ´
    -0.10
    ingroup
    -0.10
    è¯ģåĪ¸äº¤æĺĵ
    -0.10
    é¦ĸ家
    -0.09
    obox
    -0.09
    _DAYS
    -0.09
    çĭ·
    -0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.09
    åįĬ个æľĪ
    -0.09
    POSITIVE LOGITS
    æıī
    0.10
    工夫
    0.09
    åįĬ个å°ıæŶ
    0.08
    çĺ¸
    0.08
    ai
    0.08
    æľĢéķ¿
    0.08
    æ¼Ķ
    0.08
    æĪĸå¤ļ
    0.08
    uable
    0.07
    åĢĻ
    0.07
    Activations Density 0.117%

    No Known Activations