© 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. 61941
    Prev
    Next
    INDEX
    Explanations

    film review quality assessment

    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
    åºĶæľīçļĦ
    -0.09
    ä¸įåIJĮç±»åŀĭ
    -0.09
    æľĢå¿«çļĦ
    -0.08
    ponge
    -0.08
    æľĢå¿«
    -0.08
    åħħå½ĵ
    -0.08
    entially
    -0.08
    ìĸ¸
    -0.08
    积èĵĦ
    -0.08
    icum
    -0.08
    POSITIVE LOGITS
    éĥ½å¾Ī
    0.15
    ä¹Łå¾Ī
    0.14
    ä¹ŁéĿŀ常
    0.14
    å®ŀåľ¨å¤ª
    0.13
    å®ŀåľ¨æĺ¯å¤ª
    0.13
    å°±å¾Ī
    0.13
    ç®Ģ缴
    0.12
    æĻ¯èī²
    0.12
    羣çļĦå¾Ī
    0.12
    ä¹Łæĺ¯å¾Ī
    0.12
    Activations Density 0.172%

    No Known Activations