© 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. 5119
    Prev
    Next
    INDEX
    Explanations

    a specialized role or type

    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
    éĢ¡
    -0.10
    ä¸įå°½
    -0.10
    æĮĸæİĺ
    -0.09
    大纲
    -0.09
     Awakening
    -0.08
    apter
    -0.08
    æĹłçĸij
    -0.08
    è¾Ļ
    -0.08
    è°Ĵ
    -0.08
     mâ
    -0.08
    POSITIVE LOGITS
    没åĬŀæ³ķ
    0.11
    æĹłæ³ķ
    0.10
    è¿Ļ个人
    0.10
    没æľīåĬŀæ³ķ
    0.10
    没æ³ķ
    0.09
    æľ¬åľŁ
    0.08
    çļĦæĬĢæľ¯
    0.08
    çĦ¡æ³ķ
    0.08
     sacked
    0.08
     невозможно
    0.08
    Activations Density 0.012%

    No Known Activations