© 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. 12400
    Prev
    Next
    INDEX
    Explanations

    scant, sparse, limited

    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
    ected
    -0.11
     samt
    -0.09
    åĽ°å¢ĥ
    -0.09
    å¿ĥèĦı
    -0.08
    .ReadOnly
    -0.08
    éĻIJè´Ń
    -0.08
    amen
    -0.08
    岸
    -0.08
    å§ĭç»Īä¿ĿæĮģ
    -0.08
    媪
    -0.08
    POSITIVE LOGITS
    ening
    0.10
    ä¸Ģç«Ļ
    0.09
    ened
    0.09
    est
    0.09
    ities
    0.09
    ily
    0.08
    让èĩªå·±
    0.08
    è§ı
    0.08
    ockets
    0.08
    iert
    0.08
    Activations Density 0.021%

    No Known Activations