© 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. 4279
    Prev
    Next
    INDEX
    Explanations

    uv-related strings

    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
    ãģ¨ãģĦãģ£ãģ¦
    -0.11
    iÃŁ
    -0.11
    ous
    -0.10
    ëĿ¼ëıĦ
    -0.10
    ously
    -0.10
    ummer
    -0.09
    «
    -0.09
    ev
    -0.09
    éľīç´ł
    -0.09
    诳
    -0.09
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.10
    zelf
    0.09
     gì
    0.08
    etween
    0.08
     behalf
    0.08
    emm
    0.08
    uta
    0.08
    etime
    0.08
     Bernstein
    0.08
    æīĢæīĢ
    0.08
    Activations Density 0.065%

    No Known Activations