© 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. 63799
    Prev
    Next
    INDEX
    Explanations

    console application, Conservation

    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
    沤
    -0.09
    iness
    -0.09
    å°ģ
    -0.09
    å¯Įæľī
    -0.09
    æĬ½
    -0.09
    è¥ŀ
    -0.09
    ä¸įéĶĪ
    -0.08
    ä»ĩ
    -0.08
    -0.08
    åĵģä½į
    -0.08
    POSITIVE LOGITS
     Vict
    0.09
    OLE
    0.09
    çĶµæ±ł
    0.09
    ä¿Ŀå®Ī
    0.09
    anke
    0.09
     gắng
    0.09
    宽
    0.09
    moz
    0.09
    TECT
    0.09
    ysz
    0.09
    Activations Density 0.090%

    No Known Activations