© 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. 57665
    Prev
    Next
    INDEX
    Explanations

    notifications about changes

    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
    å¾Īæ·±
    -0.09
    帮å¿Ļ
    -0.09
    请éĹ®
    -0.09
    ÑĤол
    -0.09
    误导
    -0.09
    âĺī
    -0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.09
    ombat
    -0.09
    ylan
    -0.09
     TLC
    -0.08
    POSITIVE LOGITS
    ä»ĸ对
    0.10
    æĪij对
    0.10
    æľīåħ³
    0.09
    精彩
    0.09
    çļĦåĬ¨ä½ľ
    0.08
    æŃ£åľ¨è¿Ľè¡Į
    0.08
    æĽ´å¤ļ精彩
    0.08
    oso
    0.08
    é£İäºij
    0.08
    åıijçĶŁçļĦ
    0.08
    Activations Density 0.012%

    No Known Activations