© 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. 61285
    Prev
    Next
    INDEX
    Explanations

    Michel, Dornoch, Hurst, Petaluma

    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
    isse
    -0.11
    æĪijåĸľæ¬¢
    -0.10
    issa
    -0.10
    åīį身
    -0.09
    é¦ĸå¸Ń
    -0.09
    ä¸»å¼ł
    -0.09
    衽
    -0.09
     topLevel
    -0.09
    æµ·æĭĶ
    -0.08
    èĩªå·±åĸľæ¬¢
    -0.08
    POSITIVE LOGITS
    åħ¥åħļ
    0.09
     skl
    0.09
    åĽļ
    0.09
    该éĻ¢
    0.09
    èĮ´
    0.08
    便äºİ
    0.08
    为æĬĵ
    0.08
    .resolve
    0.08
    ç§ģä¸ĭ
    0.08
     Ven
    0.08
    Activations Density 0.216%

    No Known Activations