© 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. 56870
    Prev
    Next
    INDEX
    Explanations

    intact condition

    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
    ãĤĦãĤī
    -0.09
    æīĭæİĮ
    -0.09
    éļ½
    -0.09
    ç²¾é«ĵ
    -0.09
    æıIJæ¡Ī
    -0.09
    åįij
    -0.09
    æİĮ
    -0.08
    åĪ¶éĢłåķĨ
    -0.08
    _blocking
    -0.08
    _hot
    -0.08
    POSITIVE LOGITS
    交æİ¥
    0.09
    åºĵåŃĺ
    0.08
     intact
    0.08
    äºĮæīĭ
    0.08
    å½ĵæŶ
    0.08
    å¹´éĻIJ
    0.08
    åįĸ家
    0.08
     currentValue
    0.08
    ä¸Ģæīĭ
    0.08
    åĩºåĶ®
    0.08
    Activations Density 0.096%

    No Known Activations