© 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. 853
    Prev
    Next
    INDEX
    Explanations

    license agreement

    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
    ness
    -0.13
    iness
    -0.11
    turnstile
    -0.10
    æĤ´
    -0.10
    untu
    -0.09
    lish
    -0.09
    éĻħ
    -0.09
    à¸Ļาà¸Ļ
    -0.09
    çĿ£å¯Ł
    -0.08
    ÑıÑĤи
    -0.08
    POSITIVE LOGITS
    pole
    0.09
    -taking
    0.09
    edReader
    0.09
     Pole
    0.09
    aries
    0.08
    人éĥ½
    0.08
    ably
    0.08
     Islands
    0.08
    Driven
    0.08
     пÑĢедÑĥÑģ
    0.08
    Activations Density 0.122%

    No Known Activations