© 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. 7452
    Prev
    Next
    INDEX
    Explanations

    at that moment

    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
    ç¢į
    -0.10
    ç®ĹäºĨ
    -0.09
    ÑģлÑĥÑĪ
    -0.09
     Trident
    -0.08
    _RESOLUTION
    -0.08
    osex
    -0.08
    欣èµı
    -0.08
    aved
    -0.08
    好ä¸į容æĺĵ
    -0.08
    梨
    -0.08
    POSITIVE LOGITS
     moment
    0.21
    æѤåĪ»
    0.20
    è¿Ļä¸ĢåĪ»
    0.18
    æŶåĪ»
    0.17
    è¿Ļ个æŶåĢĻ
    0.17
     моменÑĤ
    0.16
     moments
    0.16
     momento
    0.15
    moment
    0.15
     Moment
    0.15
    Activations Density 0.053%

    No Known Activations