© 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. 22855
    Prev
    Next
    INDEX
    Explanations

    action ending in -ing

    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
    æľīæĿ¡ä»¶
    -0.10
    姥
    -0.10
    èĽ®
    -0.10
    äºĨåĩºæĿ¥
    -0.09
    å¾Īå¤ļæŶåĢĻ
    -0.09
    å¹³æŶ
    -0.09
    ç©
    -0.09
    åľ¨éĩĮéĿ¢
    -0.09
    alles
    -0.09
    è½»æĺĵ
    -0.09
    POSITIVE LOGITS
    åijĹ
    0.09
    inee
    0.09
    人çĶŁ
    0.08
    åĹ£
    0.08
    äºļè¿IJ
    0.08
    é¢Ĩåıĸ
    0.08
    ç»ıåİĨ
    0.08
    ä¹¾åĿ¤
    0.08
    ç»ı纬
    0.08
    ument
    0.08
    Activations Density 0.156%

    No Known Activations