© 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. 51491
    Prev
    Next
    INDEX
    Explanations

    LinkedIn

    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
    楮
    -0.09
    头çļ®
    -0.09
    é¢Īéĥ¨
    -0.09
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.09
    说åĩºæĿ¥
    -0.09
    å¥ĸéĩij
    -0.09
    梨
    -0.09
    neck
    -0.08
    类产åĵģ
    -0.08
    太太
    -0.08
    POSITIVE LOGITS
    人士
    0.12
    UES
    0.11
    гÑĥ
    0.10
    cion
    0.09
    olie
    0.08
    acier
    0.08
    ues
    0.08
    ä¸įèĪį
    0.08
    erral
    0.08
    ик
    0.08
    Activations Density 0.005%

    No Known Activations