© 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. 34781
    Prev
    Next
    INDEX
    Explanations

    tournament or championship games

    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
     Cecil
    -0.08
    ä¾Ľå¤§å®¶
    -0.08
    è¿Ļè¾ĪåŃIJ
    -0.08
    大åѦæ¯ķä¸ļ
    -0.08
    èµĪ
    -0.08
    =new
    -0.08
    åŁ
    -0.08
    åĨĢ
    -0.08
    æ°ijä¼Ĺ
    -0.08
    åľ¨è¿Ļç§į
    -0.08
    POSITIVE LOGITS
    çݯèĬĤ
    0.10
    è¿ĽåĨĽ
    0.10
    -tier
    0.09
    æīij
    0.09
    åĽŃåĮº
    0.09
    çĶŁæŃ»
    0.09
    _limits
    0.09
     Powered
    0.09
    æĢ»å±Ģ
    0.08
    _php
    0.08
    Activations Density 0.242%

    No Known Activations