© 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. 6848
    Prev
    Next
    INDEX
    Explanations

    attention to detail

    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
    ishing
    -0.09
     ÑħÑĢ
    -0.09
    nod
    -0.08
    èĢĢ
    -0.08
     verbosity
    -0.08
    lac
    -0.08
    å½·
    -0.08
    лим
    -0.08
    ä½ı
    -0.08
    brick
    -0.08
    POSITIVE LOGITS
    ç»ĨèĬĤ
    0.12
     detail
    0.11
    å¾Īå°ı
    0.10
     Detail
    0.09
    麻çĹ¹
    0.09
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.09
    /detail
    0.09
    ä»İæĿ¥æ²¡æľī
    0.09
     Details
    0.09
    äºĭåħ³
    0.09
    Activations Density 0.008%

    No Known Activations