© 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. 16634
    Prev
    Next
    INDEX
    Explanations

    Erlang, OTP, Elixir, bit syntax

    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
    ä¸ĢåĪĢ
    -0.10
    æ¹Ħ
    -0.10
    ãĤ³ãĥ¬
    -0.09
    éĺĨ
    -0.09
     ÑħÑĢ
    -0.09
    æŶåĪ»
    -0.09
    ãĤ·ãĥª
    -0.08
    æĪIJéĥ½
    -0.08
     iss
    -0.08
    alla
    -0.08
    POSITIVE LOGITS
    å·§
    0.10
    apur
    0.09
     Gul
    0.08
     Erl
    0.08
    çģı
    0.08
    asd
    0.08
     OTP
    0.08
     Tubes
    0.07
     Finland
    0.07
    elow
    0.07
    Activations Density 0.087%

    No Known Activations