© 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. 21285
    Prev
    Next
    INDEX
    Explanations

    City Express

    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
    anship
    -0.11
    涯
    -0.10
    ä¸Ģ线åŁİå¸Ĥ
    -0.10
    ä¼¢
    -0.10
    åħ¬çĽĬæ´»åĬ¨
    -0.09
    èĥĦ
    -0.09
    åĬŀåħ¬åİħ
    -0.09
    uzzer
    -0.09
    人æµģ
    -0.09
    ploy
    -0.09
    POSITIVE LOGITS
    8
    0.09
    çļĦæĥħæĦŁ
    0.09
    enton
    0.09
    9
    0.09
    7
    0.09
    5
    0.08
    ave
    0.08
    3
    0.08
    0
    0.08
    å¥ī
    0.08
    Activations Density 0.003%

    No Known Activations