© 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. 40195
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    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
    elu
    -0.11
    ä¸įåı¯æĢĿè®®
    -0.10
    åī§
    -0.10
    è¸ıåħ¥
    -0.09
    æį¢äºĨ
    -0.09
    æį¢
    -0.08
    è®Ń
    -0.08
     Dez
    -0.08
    颦
    -0.08
     Boulevard
    -0.08
    POSITIVE LOGITS
    åĢĴ
    0.10
    éĥ½è¯´
    0.10
    è¿ĩåħ³
    0.09
    å°ıå°ı
    0.08
    å¼ĥ
    0.08
    iously
    0.08
     Subjects
    0.08
    é»ĦåŁĶ
    0.08
    atcher
    0.08
    cept
    0.08
    Activations Density 0.073%

    No Known Activations