© 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. 38271
    Prev
    Next
    INDEX
    Explanations

    flash and related concepts

    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
    çĸı
    -0.11
    hesive
    -0.11
    usan
    -0.10
    -mf
    -0.09
    _spin
    -0.09
    ë¬ĺ
    -0.09
    /linux
    -0.09
    éĢļä¿Ĺ
    -0.09
    /rss
    -0.09
    æ°Ķæ°Ľ
    -0.09
    POSITIVE LOGITS
    ä¸ĢéĹª
    0.12
     flash
    0.12
    éĹªåħī
    0.11
    .flash
    0.10
    Flash
    0.10
    éĹ´
    0.10
    -flash
    0.10
    éĹª
    0.09
     flashes
    0.09
    FLASH
    0.09
    Activations Density 0.049%

    No Known Activations