© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9871
    Prev
    Next
    INDEX
    Explanations

    herbal medicine prescriptions and remedies

    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
    åĿı
    -0.09
    æĵį
    -0.09
    åģ¥åº·
    -0.09
    è·ª
    -0.09
    .FAIL
    -0.09
    ÄŁi
    -0.08
    èĤ¯
    -0.08
    REC
    -0.08
    .Span
    -0.08
    å¹£
    -0.08
    POSITIVE LOGITS
     Tall
    0.10
    社ä¿Ŀ
    0.09
    æĢĸ
    0.09
    大象
    0.08
    åĮ®ä¹ı
    0.08
    åIJĪä¸Ģ
    0.08
    åįģä¸īå±Ĭ
    0.08
    logical
    0.08
     tall
    0.08
    .AppSettings
    0.08
    Activations Density 0.012%

    No Known Activations