© 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. 32487
    Prev
    Next
    INDEX
    Explanations

    name as published or listed

    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
    ron
    -0.10
    inters
    -0.09
    ä¼ģä¸ļæıIJä¾Ľ
    -0.09
    æĬĬèĩªå·±
    -0.09
    rons
    -0.09
    å¾Ĺä½ı
    -0.09
    åIJī
    -0.08
     alike
    -0.08
    -INF
    -0.08
    Expose
    -0.08
    POSITIVE LOGITS
    宪
    0.09
    庵
    0.09
    ä¸įåĪĨ
    0.09
    å¿Ŀ
    0.09
    好åĿı
    0.08
     Scalars
    0.08
    åľ¨åħ¨çIJĥ
    0.08
    æĴŃ
    0.08
    ä½ľä¸ºä¸Ģç§į
    0.08
    èķĬ
    0.08
    Activations Density 0.032%

    No Known Activations