© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36623
    Prev
    Next
    INDEX
    Explanations

    brought up

    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
    _focus
    -0.10
    说å¾Ĺ
    -0.09
    ENS
    -0.09
    亲
    -0.09
    èĤļ
    -0.09
    owing
    -0.08
    ADS
    -0.08
    åıįè¿ĩæĿ¥
    -0.08
    itics
    -0.08
    æĬ¥æ¡Ī
    -0.08
    POSITIVE LOGITS
    åIJĮåŁİ
    0.09
    æ´ŀ
    0.08
    è¡·
    0.08
    以åħį
    0.08
    fee
    0.08
    SES
    0.08
    èµĽåIJİ
    0.08
    _WINDOW
    0.08
    åĢ¼å¾Ĺåħ³æ³¨
    0.08
    éĻ¤å¤ķ
    0.08
    Activations Density 0.012%

    No Known Activations