© 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. 29685
    Prev
    Next
    INDEX
    Explanations

    5 or multiples of 5

    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
    upil
    -0.10
    upo
    -0.10
    rior
    -0.09
    失误
    -0.09
    ableObject
    -0.08
    kest
    -0.08
    ÑģÑĤ
    -0.08
    iten
    -0.08
    uario
    -0.08
    oci
    -0.08
    POSITIVE LOGITS
    å¿ĥæĦ¿
    0.10
    æļ§æĺ§
    0.09
    æ·®åįĹ
    0.09
    è¿ĻåĦ¿
    0.09
    å¹´æĿ¥
    0.08
    ary
    0.08
    еÑģÑĤÑĮ
    0.08
    æĤłæĤł
    0.08
    bir
    0.08
    ï¸
    0.08
    Activations Density 0.084%

    No Known Activations