© 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. 58477
    Prev
    Next
    INDEX
    Explanations

    Thermo, duromine, Continuation War

    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
    tls
    -0.09
    æĶ¹éĿ©åĪĽæĸ°
    -0.09
    ãĤ¢ãĤ¦
    -0.09
    èĢĮä¸Ķè¿ĺ
    -0.08
    åĴĿ
    -0.08
    æŶéĹ´åĴĮ
    -0.08
    /welcome
    -0.08
    æĢĽ
    -0.08
    ç»ıéªĮåĴĮ
    -0.08
    xin
    -0.08
    POSITIVE LOGITS
    åĪĻæĺ¯
    0.11
    åľ¨ä¸ĢæĹģ
    0.10
    amp
    0.10
    åĪĻ
    0.10
     meanwhile
    0.09
     equally
    0.09
    éĤ£è¾¹
    0.08
     ìĹŃìĭľ
    0.08
    èĻİ
    0.08
    åIJĮçŃī
    0.08
    Activations Density 0.621%

    No Known Activations