© 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. 47737
    Prev
    Next
    INDEX
    Explanations

    list markers like * and +

    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
    èĭ±çī¹
    -0.12
    èݽ
    -0.10
    çĦ¶æĺ¯
    -0.09
    ç´§å¯Ĩç»ĵåIJĪ
    -0.09
    æ¡IJ
    -0.08
    空çĻ½
    -0.08
    æŀī
    -0.08
     Saul
    -0.08
    é¦
    -0.08
     comp
    -0.08
    POSITIVE LOGITS
    iswa
    0.09
     Tribune
    0.09
    å¿Į
    0.09
    erot
    0.09
    èijĽ
    0.09
    eria
    0.09
    .annot
    0.09
    editable
    0.09
     dise
    0.09
    itä
    0.08
    Activations Density 0.147%

    No Known Activations