© 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. 49815
    Prev
    Next
    INDEX
    Explanations

    Comparative Literature, examines, Story

    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
    åĶ¾
    -0.10
    ä¹Łè®¸æĺ¯
    -0.09
    aval
    -0.09
    æľ«
    -0.09
    禾
    -0.09
    æ§İ
    -0.09
    .samples
    -0.09
    èī¯
    -0.09
    .sound
    -0.08
    ä¸ŃåįİæĸĩåĮĸ
    -0.08
    POSITIVE LOGITS
    æĶ¿åħļ
    0.11
    å¢ŀæ·»äºĨ
    0.09
    elite
    0.09
    åħļåĨħ
    0.09
    plural
    0.09
    æİ£
    0.08
    леÑĢ
    0.08
    æŀIJ
    0.08
    çķĽ
    0.08
     plural
    0.08
    Activations Density 0.097%

    No Known Activations