© 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. 11667
    Prev
    Next
    INDEX
    Explanations

    interdisciplinary and multidisciplinary teams

    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
    騰
    -0.10
    èħ¾
    -0.09
    æĻ®åıĬ
    -0.09
    ä¹¾åĿ¤
    -0.09
    æĹłèģĬ
    -0.08
    VELO
    -0.08
    顺
    -0.08
    eli
    -0.08
    ICY
    -0.08
    åįĹéĥ¨
    -0.08
    POSITIVE LOGITS
    交åıī
    0.19
    è·¨
    0.16
    è·¨çķĮ
    0.15
     cross
    0.15
    cross
    0.12
    (team
    0.12
    .cross
    0.12
    Cross
    0.12
    åѦç§ij
    0.12
    åĽ¢éĺŁ
    0.11
    Activations Density 0.131%

    No Known Activations