© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36570
    Prev
    Next
    INDEX
    Explanations

    Batman, Joker, Responsibility

    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¿ģ移
    -0.10
    è¯ij
    -0.10
    çģĮ
    -0.09
    èĻ±
    -0.09
    éģ·
    -0.09
    èĥĸ
    -0.09
    çİ¢
    -0.09
    æłı缮
    -0.09
    æĦ¿
    -0.09
    æIJĶ
    -0.08
    POSITIVE LOGITS
    çĬ¯ç½ª
    0.10
     Batman
    0.10
    åĪijäºĭæ¡Ī件
    0.09
    æŀŃ
    0.09
    Batman
    0.09
    èĿĻ
    0.09
    æ¬ł
    0.08
     uda
    0.08
    æĬĹçĻĮ
    0.08
    etti
    0.08
    Activations Density 0.066%

    No Known Activations