© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16551
    Prev
    Next
    INDEX
    Explanations

    clever

    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
    Negative Logits
    累累
    -0.10
    èĽİ
    -0.10
    nist
    -0.09
    amble
    -0.09
     thiá»ĥu
    -0.09
     اÙĦÙĥرÙĬÙħ
    -0.09
    istani
    -0.09
    íĤ¹
    -0.09
    ä¸ķ
    -0.09
     кÑĢови
    -0.09
    POSITIVE LOGITS
    ness
    0.18
    NESS
    0.14
    ly
    0.13
    ened
    0.12
    arium
    0.11
    Enough
    0.10
     enough
    0.10
    æĹłæ¯Ķ
    0.10
    wort
    0.10
    é«ĺæķĪçļĦ
    0.09
    Activations Density 0.003%

    No Known Activations