© 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. 63220
    Prev
    Next
    INDEX
    Explanations

    hold liable

    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
    èĺijèıĩ
    -0.09
    (nil
    -0.09
    ALES
    -0.09
    nil
    -0.09
    год
    -0.09
    æľīæĿ¡ä»¶
    -0.08
    ä¸Ģçľ¼
    -0.08
    忤
    -0.08
    èĺij
    -0.08
    è¡·å¿ĥ
    -0.08
    POSITIVE LOGITS
     accountable
    0.13
    æijĬ
    0.12
    ä¸įä½ı
    0.12
    ä½ıäºĨ
    0.12
    å¾Ĺä½ı
    0.11
     hostage
    0.11
    hold
    0.10
     alo
    0.10
    å¹´ä¹ĭä¹ħ
    0.10
     sway
    0.10
    Activations Density 0.225%

    No Known Activations