© 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. 51059
    Prev
    Next
    INDEX
    Explanations

    confidence intervals

    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
    çIJĨç§ij
    -0.11
    çIJĨå·¥
    -0.11
    éĿ¢è²Į
    -0.10
    顶
    -0.10
    annah
    -0.10
    ä½ĵåĪ¶
    -0.09
    osal
    -0.09
    éłĤ
    -0.09
    æĺ¯ä¸įåı¯èĥ½
    -0.09
    ç§ĥ
    -0.09
    POSITIVE LOGITS
    è¯ģæį®
    0.09
    家çĶ¨
    0.09
    åĮħåĽ´
    0.08
    Span
    0.08
    å·¥ä½ľæĬ¥åijĬ
    0.08
    olon
    0.08
    Haz
    0.08
    Invoker
    0.08
     confidence
    0.07
     ine
    0.07
    Activations Density 0.070%

    No Known Activations