© 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. 29770
    Prev
    Next
    INDEX
    Explanations

    reading data from sources

    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
    ounge
    -0.10
    WithValue
    -0.10
    .Identifier
    -0.09
     Susp
    -0.09
    .createClass
    -0.09
    emain
    -0.09
    .Created
    -0.09
     ÙĪاÙĦÙģ
    -0.09
    .appspot
    -0.09
    ä¹īåĬ¡
    -0.09
    POSITIVE LOGITS
    èİ·åıĸ
    0.12
    ä½Ĩä»İ
    0.10
    读
    0.10
    读åIJİ
    0.10
    AsString
    0.10
     from
    0.10
    æıIJåıĸ
    0.10
     èİ·åıĸ
    0.09
    OrDefault
    0.09
    .read
    0.09
    Activations Density 1.250%

    No Known Activations