© 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. 40172
    Prev
    Next
    INDEX
    Explanations

    legal cases and arrests

    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
    æ´¹
    -0.10
    享
    -0.10
    ç©¿è¡£
    -0.10
    èĩªèIJ¥
    -0.09
    å°ıå·§
    -0.09
    ein
    -0.09
    æ·«
    -0.09
     дол
    -0.09
    ãģ£ãģ±
    -0.09
    ä¸ĢèĦļ
    -0.09
    POSITIVE LOGITS
    åĨ¤
    0.14
    æĹłè¾ľ
    0.11
    鸣
    0.11
    DNA
    0.10
     innocence
    0.10
    afia
    0.10
    信念
    0.09
    辩æĬ¤
    0.09
    igar
    0.09
     fals
    0.09
    Activations Density 0.046%

    No Known Activations