© 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. 18533
    Prev
    Next
    INDEX
    Explanations

    reporting names and places

    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
    łģ
    -0.09
    éĿ¶
    -0.09
    大åŀĭ
    -0.09
    åħļåĴĮåĽ½å®¶
    -0.08
    sWith
    -0.08
    Ùħرا
    -0.08
    _Application
    -0.08
    éģ½
    -0.08
    åľ°ä¸ĭæ°´
    -0.08
    kil
    -0.08
    POSITIVE LOGITS
     Pron
    0.08
    merc
    0.08
    åĪĨæŀIJå¸Ī
    0.08
     Sho
    0.08
    iosity
    0.08
     Olympics
    0.08
    æı¡æīĭ
    0.08
    Editors
    0.08
    0
    0.08
    æ´Ĺ礼
    0.08
    Activations Density 0.014%

    No Known Activations