© 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. 57051
    Prev
    Next
    INDEX
    Explanations

    story, stories, posts

    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
    isoft
    -0.09
     dist
    -0.09
    wend
    -0.08
     Hispan
    -0.08
    .Buffer
    -0.08
    åŃIJå¼Ł
    -0.08
    åįķåįķ
    -0.08
    æݾ
    -0.08
    ä¸Ģ个èģĮä¸ļ
    -0.08
    å¸Ĥéķ¿
    -0.08
    POSITIVE LOGITS
    enor
    0.10
    andi
    0.09
    订
    0.09
     ÑĦин
    0.09
    æĬĴ
    0.09
    å²Į
    0.08
    خار
    0.08
    qtt
    0.08
    ALAR
    0.08
    宿
    0.08
    Activations Density 0.001%

    No Known Activations