© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 62974
    Prev
    Next
    INDEX
    Explanations

    keratinocytes, cornea, keratosis, corneum

    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
    ä¸įæĿ¥
    -0.11
    olley
    -0.10
    æīĵçĿĢ
    -0.09
    è·¯ä¸Ĭ
    -0.09
    åľĥ
    -0.09
    çĵ¶åŃIJ
    -0.09
    å¨Ĩ
    -0.09
    殳
    -0.09
    æľĪ亮
    -0.09
    Hal
    -0.09
    POSITIVE LOGITS
     ker
    0.10
    KER
    0.09
     Ker
    0.09
     liá»ĩt
    0.09
    ker
    0.09
    宿
    0.09
     tens
    0.08
    .ft
    0.08
    resh
    0.08
    é³ŀ
    0.08
    Activations Density 0.220%

    No Known Activations