© 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. 32217
    Prev
    Next
    INDEX
    Explanations

    join us on

    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
    顺
    -0.09
    ç½Ķ
    -0.09
    æı½
    -0.09
    å®
    -0.09
    åĪĽæĸ°èĥ½åĬĽ
    -0.09
     Bronze
    -0.08
    éĿĴéĵľ
    -0.08
    äºĨèĩªå·±çļĦ
    -0.08
    ä¿ĿæĮģçĿĢ
    -0.08
    æĿµ
    -0.08
    POSITIVE LOGITS
    ä¸Ģèµ·åİ»
    0.12
    obl
    0.09
    æĹ¢æľī
    0.09
    åħ±åIJĮ
    0.09
    á»ijc
    0.09
     hô
    0.08
    æݢ讨
    0.08
    çĨŁæĤīçļĦ
    0.08
    .getBounds
    0.08
    é¡
    0.08
    Activations Density 0.042%

    No Known Activations