© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18233
    Prev
    Next
    INDEX
    Explanations

    ulceration

    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
    姿æĢģ
    -0.09
    åįģ足
    -0.09
    rup
    -0.09
     Mant
    -0.08
    tl
    -0.08
    pty
    -0.08
    åģ¿
    -0.08
     staat
    -0.08
    yer
    -0.08
    æľĢæĸ°çļĦ
    -0.08
    POSITIVE LOGITS
    累累
    0.11
    ateur
    0.11
    ../../../
    0.09
    çĶ¨è½¦
    0.09
    æĪ¢
    0.09
    pons
    0.09
    èĪ¬
    0.09
    åĸĭ
    0.08
    åľ°å¸¦
    0.08
     dụng
    0.08
    Activations Density 0.062%

    No Known Activations