© 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. 20021
    Prev
    Next
    INDEX
    Explanations

    reasoning and justification

    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
    çķĮ
    -0.11
    夺
    -0.09
     Æ¡n
    -0.08
    endum
    -0.08
    SURE
    -0.08
    åı¯ä¸įæĺ¯
    -0.08
    足以
    -0.08
    гÑĢан
    -0.08
    .Deep
    -0.08
    åĭģ
    -0.08
    POSITIVE LOGITS
    çIJĨçĶ±
    0.16
    çļĦçIJĨçĶ±
    0.15
     reasons
    0.11
    å«Į
    0.11
    认为
    0.11
    å®ŀåľ¨å¤ª
    0.10
    害æĢķ
    0.10
    ç§įç§į
    0.10
     ìĿ´ìľł
    0.10
    èĢĥèĻijåĪ°
    0.10
    Activations Density 0.159%

    No Known Activations