© 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. 23041
    Prev
    Next
    INDEX
    Explanations

    .js files

    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
    åĪĨå±Ģ
    -0.11
    arios
    -0.09
    èĩªæķij
    -0.09
    æİīäºĨ
    -0.09
    èļĮ
    -0.09
    æIJĵ
    -0.08
    æ±Łä¸ľ
    -0.08
    寡
    -0.08
    ãĤĬãģ¾ãģĻ
    -0.08
    æĸ¹éĿ¢çļĦ
    -0.08
    POSITIVE LOGITS
    å¼ĢèĬ±
    0.09
    OrNull
    0.09
    лей
    0.09
    ada
    0.08
    lector
    0.08
    istani
    0.08
    éĿŀ常åĸľæ¬¢
    0.08
    ãģªãĤĭ
    0.08
    OMIC
    0.08
    alties
    0.08
    Activations Density 0.072%

    No Known Activations