© 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. 901
    Prev
    Next
    INDEX
    Explanations

    said or says

    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
    å¨ĵ
    -0.11
    èĭ¦èĭ¦
    -0.10
    èĥĥåı£
    -0.10
    .LA
    -0.10
    èĩªä¿¡
    -0.10
    éĩįæĸ°
    -0.10
    çľ¼åīį
    -0.10
    æĢ¦
    -0.09
    详ç»Ĩä»ĭç»į
    -0.09
    èµ°ä¸ĭåİ»
    -0.09
    POSITIVE LOGITS
    è¡Ļ
    0.08
     Blo
    0.07
    á»ĵn
    0.07
    CAD
    0.07
    çŁŃ缺
    0.07
     PIO
    0.07
    IAL
    0.07
    FIX
    0.07
    å¾®åįļ
    0.07
    æ¶Īéĺ²
    0.07
    Activations Density 0.040%

    No Known Activations