© 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. 26073
    Prev
    Next
    INDEX
    Explanations

    off-the-box / built-in / running

    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
    hek
    -0.09
    arial
    -0.09
    å·¦æīĭ
    -0.09
    .ZERO
    -0.09
    ogg
    -0.09
     wrongdoing
    -0.08
    æĹģ
    -0.08
    гÑĢÑĥз
    -0.08
    atus
    -0.08
    Ñģад
    -0.08
    POSITIVE LOGITS
     Bri
    0.09
    åIJĵå¾Ĺ
    0.09
    rary
    0.08
    ?url
    0.08
    a
    0.08
    çĪ±å¿ĥ
    0.08
    ä¸Ģ人
    0.08
    è¿ĩ硬
    0.08
    çĸĨ
    0.08
    eren
    0.08
    Activations Density 0.009%

    No Known Activations