© 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. 26401
    Prev
    Next
    INDEX
    Explanations

    financial indices and commodities

    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
    emd
    -0.09
    æĬķ
    -0.08
    å·¦åı³
    -0.08
    dock
    -0.07
     raz
    -0.07
    itial
    -0.07
    olic
    -0.07
    åıijçĹħ
    -0.07
    éŨåı£
    -0.07
    椽
    -0.07
    POSITIVE LOGITS
    åIJĦ项
    0.10
    ä¸Ģ举
    0.10
    ä¸Ģå¤ľ
    0.10
    ä¸Ģåı£æ°Ķ
    0.10
    çĸ
    0.09
    æĭĬ
    0.09
    åŃ¢
    0.09
    insi
    0.09
    ä¸Ģè·¯ä¸Ĭ
    0.09
    immers
    0.09
    Activations Density 0.025%

    No Known Activations