© 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. 7638
    Prev
    Next
    INDEX
    Explanations

    following conditions

    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
    èĪį
    -0.09
    çºł
    -0.08
    管çIJĨåijĺ
    -0.08
    æıĨ
    -0.08
    å¼Ĥ
    -0.08
    Vect
    -0.07
    å°±æĺ¯ä¸ºäºĨ
    -0.07
     khắc
    -0.07
    ç¿»
    -0.07
    Kind
    -0.07
    POSITIVE LOGITS
    jad
    0.09
    ÑĢаниÑĨ
    0.09
    гÑĥ
    0.09
    çIJħ
    0.09
    轻轻
    0.09
    erot
    0.09
    ãģıãģł
    0.09
    /loading
    0.09
    داÙĨ
    0.09
    ä¸Ģç»Ħ
    0.09
    Activations Density 0.130%

    No Known Activations