© 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. 60896
    Prev
    Next
    INDEX
    Explanations

    family, parents, owners

    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
    antine
    -0.09
    æ¢Ĺ
    -0.09
    ãĤ¢ãĤ¦ãĥĪ
    -0.08
    å®īå¨ľ
    -0.08
    èĩªæľī
    -0.08
    寮
    -0.08
    urus
    -0.08
    çıĤ
    -0.08
    åį³ä½¿æĺ¯
    -0.08
    纯粹
    -0.08
    POSITIVE LOGITS
    家åºŃ
    0.11
     ÑħозÑı
    0.10
    çĶ¨æĪ·çļĦ
    0.10
    주ìĭľ
    0.09
    å¼łåħĪçĶŁ
    0.09
    terr
    0.09
    DidChange
    0.09
    åĬ¡
    0.09
    åĨľæĪ·
    0.09
     Families
    0.09
    Activations Density 0.025%

    No Known Activations