© 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. 30195
    Prev
    Next
    INDEX
    Explanations

    Restaurant Group

    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
    èĮĦ
    -0.10
    类似çļĦ
    -0.09
    éĢ¼
    -0.09
    æĪĸèĢħ说
    -0.09
    ︱
    -0.08
    bes
    -0.08
    åħ¨éķ¿
    -0.08
    Neal
    -0.08
    æŁIJç§į
    -0.08
    Scalars
    -0.08
    POSITIVE LOGITS
    ç»ĻåĬĽ
    0.11
    åįıåĬŀ
    0.10
     lyon
    0.09
    annis
    0.09
    ä¼ģä¸ļæıIJä¾Ľ
    0.09
     vot
    0.09
    大åĬĽæĶ¯æĮģ
    0.09
    éħĴä¸ļ
    0.08
    容å¿į
    0.08
    ernet
    0.08
    Activations Density 0.036%

    No Known Activations