© 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. 64130
    Prev
    Next
    INDEX
    Explanations

    entrusted to, your life, leaving it

    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
    à´³
    -0.12
    ÑĪин
    -0.10
    STANCE
    -0.10
    æĹ¢
    -0.09
    éĨ´
    -0.09
    WAYS
    -0.09
     prac
    -0.09
    éĢ¼
    -0.08
    è¿°
    -0.08
    æī¼
    -0.08
    POSITIVE LOGITS
    交ç»Ļ
    0.17
    ä»»ãģĽ
    0.12
    å§Ķæīĺ
    0.12
     entrusted
    0.11
    åįĸç»Ļ
    0.10
    身åIJİ
    0.10
    çķĻç»Ļ
    0.10
    ä¾ĿéĿł
    0.09
    èIJ½åĪ°
    0.09
    è´£
    0.09
    Activations Density 0.032%

    No Known Activations