© 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. 63756
    Prev
    Next
    INDEX
    Explanations

    claim, claiming, claimed

    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
    俱
    -0.10
    elen
    -0.09
    landers
    -0.09
    elman
    -0.09
    bour
    -0.08
    loff
    -0.08
    积æŀģæİ¨è¿Ľ
    -0.08
    åĪ³
    -0.08
    à¹ģà¸ľà¸Ļ
    -0.08
    æĮģæľī
    -0.08
    POSITIVE LOGITS
    é³Į
    0.10
    UV
    0.10
     ÑĥÑĩаÑģÑĤие
    0.10
    ency
    0.09
    slot
    0.09
    eping
    0.08
     Friendship
    0.08
     Glück
    0.08
    建éĢł
    0.08
    èݪ
    0.08
    Activations Density 0.018%

    No Known Activations