© 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. 54724
    Prev
    Next
    INDEX
    Explanations

    dare to venture

    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
    è¿Ĥ
    -0.09
     обо
    -0.09
    ä¸įåı¯éģ¿åħį
    -0.09
    注å®ļ
    -0.09
    ä¸Ģ大
    -0.09
    å¿ħå®ļ
    -0.08
    çĿ¿
    -0.08
    æīįä¼ļ
    -0.08
    èĥ¡åŃIJ
    -0.08
    rees
    -0.08
    POSITIVE LOGITS
    æĭ¿åĩºæĿ¥
    0.10
     Wend
    0.09
    æľīä»»ä½ķ
    0.09
    ä¸įæķ¢
    0.09
    æ¶ī足
    0.09
    éĥ½ä¸įæķ¢
    0.09
    称ä¹ĭ
    0.09
    æĢł
    0.08
    åĬłåħ¥
    0.08
    عا
    0.08
    Activations Density 0.011%

    No Known Activations