© 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. 3037
    Prev
    Next
    INDEX
    Explanations

    line followed by other words

    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
    æĵİ
    -0.11
    éªĿ
    -0.10
    è¿ĻæĿ¡
    -0.09
    .providers
    -0.09
    è¿ĻæĶ¯
    -0.09
    ä¸ĢåĪ»
    -0.08
    çļĦéĤ£ä¸Ģ
    -0.08
    çݺ
    -0.08
    áĥ¦
    -0.08
    æ±Ģ
    -0.08
    POSITIVE LOGITS
    ä¸įæĺİçĻ½
    0.09
    versed
    0.09
    anca
    0.08
    æĪijå¸Ĥ
    0.08
    eted
    0.08
    umes
    0.08
    ä¸įäºĨ解
    0.08
    sez
    0.08
    ests
    0.08
    prises
    0.08
    Activations Density 0.037%

    No Known Activations