© 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. 38223
    Prev
    Next
    INDEX
    Explanations

    ready to drop

    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
    æĹ¢æĺ¯
    -0.11
    ä¸Ģè§Ī
    -0.11
    çªģåıij
    -0.09
    绣çŃ¹æİ¨è¿Ľ
    -0.09
    _MAIN
    -0.09
    ä¸Ģä¸ĭåŃIJ
    -0.08
    åįģ足
    -0.08
    ç«Ł
    -0.08
    éļ¾æĢª
    -0.08
    exo
    -0.08
    POSITIVE LOGITS
    æŃ£åľ¨
    0.23
    缮åīįæŃ£åľ¨
    0.21
    æŃ£åľ¨è¿Ľè¡Į
    0.21
    缮åīįå·²ç»ı
    0.17
    åį³å°Ĩ
    0.17
     Äijang
    0.16
    å°ļæľª
    0.16
    å°Ĩäºİ
    0.16
    å¾ħ
    0.15
    缮åīįå·²
    0.15
    Activations Density 0.137%

    No Known Activations