© 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. 22938
    Prev
    Next
    INDEX
    Explanations

    lessons learned from past events

    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©æĻ¨
    -0.10
    çªģå¦Ĥåħ¶æĿ¥
    -0.09
    èµı
    -0.09
    åĮħ
    -0.09
    æķ´å¤©
    -0.08
    åĪĽå»ºå·¥ä½ľ
    -0.08
    ä¾ĽéľĢ
    -0.08
    çªģå¦Ĥåħ¶
    -0.08
    <<
    -0.08
    åģ¶çĦ¶
    -0.08
    POSITIVE LOGITS
    æķĻè®Ń
    0.17
    åIJ¸åıĸ
    0.16
    åѦåĪ°
    0.13
    æĢ»ç»ĵ
    0.11
     lessons
    0.11
    ç»ıéªĮåĴĮ
    0.10
    ç»ıéªĮ
    0.10
    åĢŁéī´
    0.10
     Lessons
    0.10
    æī¬
    0.10
    Activations Density 0.039%

    No Known Activations