© 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. 38279
    Prev
    Next
    INDEX
    Explanations

    an, a, an, naturally, UPDATE

    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¿Ļæī¹
    -0.11
    ç½¢äºĨ
    -0.11
    å¥
    -0.11
    è¿Ļç±»
    -0.10
    ä½ķåĨµ
    -0.10
    è¿Ļå¥Ĺ
    -0.09
    çīĴ
    -0.09
    å°ıçĶ·åŃ©
    -0.09
    åīįåĪĹ
    -0.09
    æĬĢæľ¯æľįåĬ¡
    -0.09
    POSITIVE LOGITS
    -how
    0.08
    羣çļĦæĺ¯
    0.08
    åķ§
    0.08
    究竣
    0.08
    å¦Ĥä½ķ
    0.08
    ç»Īæŀģ
    0.08
    究竣æĺ¯
    0.08
    å¤ļå°ij
    0.08
    çĤ¹æ»´
    0.08
     Cul
    0.08
    Activations Density 0.272%

    No Known Activations