© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32801
    Prev
    Next
    INDEX
    Explanations

    idle time or inactivity

    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
    ãĤ¹ãĤ¿
    -0.10
    æĽ¿ä»£
    -0.09
    ATAR
    -0.09
    æ°ij主çĶŁæ´»
    -0.09
    orld
    -0.09
    ầm
    -0.09
     ìĦ
    -0.09
    ä»£æĽ¿
    -0.09
    _pb
    -0.09
    太åIJİ
    -0.09
    POSITIVE LOGITS
     idle
    0.20
    éĹ²
    0.19
    éĹ²ç½®
    0.18
    _idle
    0.18
     Idle
    0.17
    Idle
    0.16
    idle
    0.15
    _IDLE
    0.14
     inactive
    0.13
    ä¼ijæģ¯
    0.13
    Activations Density 0.064%

    No Known Activations