© 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. 63786
    Prev
    Next
    INDEX
    Explanations

    stakeholders

    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
    ONLY
    -0.09
    æ°ijæĶ¿
    -0.08
    ague
    -0.08
    æŁłæª¬
    -0.08
    -packages
    -0.08
    åķĨä¸ļåĮĸ
    -0.08
    ä¿Ń
    -0.08
    æīij
    -0.08
    å°ļ
    -0.08
    ATO
    -0.08
    POSITIVE LOGITS
     Stake
    0.17
     stake
    0.17
     stakeholders
    0.16
     stakes
    0.14
    èĤ¡ä¸ľ
    0.12
    stakes
    0.11
    ä»İæĿ¥æ²¡æľī
    0.10
    åĪ©çĽĬ
    0.09
    æİ¥
    0.09
    çļĦåĪ©çĽĬ
    0.09
    Activations Density 0.020%

    No Known Activations