© 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. 16839
    Prev
    Next
    INDEX
    Explanations

    championships and titles

    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
    å¿ĥæĻº
    -0.09
    ØŃÙĬ
    -0.09
    cription
    -0.09
    èĭŁ
    -0.08
    éĩįæķ´
    -0.08
    åĿĩè¡¡
    -0.08
    ARN
    -0.08
    alone
    -0.08
    ç®į
    -0.08
    å°ij
    -0.08
    POSITIVE LOGITS
    çIJĥåijĺ
    0.11
    çħŀ
    0.11
    ä¸Ģ家
    0.11
     players
    0.10
    éĺŁåijĺ
    0.10
    ä¼łçIJĥ
    0.10
    åľºä¸Ĭ
    0.10
    สะà¸Ķ
    0.10
    çIJĥæĺŁ
    0.10
    峡
    0.09
    Activations Density 0.481%

    No Known Activations