© 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. 29394
    Prev
    Next
    INDEX
    Explanations

    data analysis

    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
    åħ¨æ°ij
    -0.10
    è¹²
    -0.09
    ç»ıèIJ¥èĢħ
    -0.09
    zia
    -0.09
    åħ¨èº«
    -0.09
    榷
    -0.09
    isas
    -0.09
     pedest
    -0.09
    arb
    -0.08
    èĬ½
    -0.08
    POSITIVE LOGITS
     одно
    0.10
    ç¼ķ
    0.09
    åħļé£İ
    0.09
    å±Ĥå±Ĥ
    0.09
    odor
    0.09
    sav
    0.09
    åķ¡
    0.09
     Field
    0.08
     Bryant
    0.08
    æīĵãģ¡
    0.08
    Activations Density 0.103%

    No Known Activations