© 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. 60946
    Prev
    Next
    INDEX
    Explanations

    rolling, roll, rolled

    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
    ittest
    -0.10
    à¸łà¸²à¸ŀ
    -0.09
    ahren
    -0.09
     ÑģÑĤо
    -0.09
    aket
    -0.09
    æĴij
    -0.09
    çĹĩ
    -0.09
    akeup
    -0.09
    ä¸Ģæľµ
    -0.09
    æ¸ļ
    -0.09
    POSITIVE LOGITS
    æ»ļ
    0.17
     roll
    0.14
    -roll
    0.14
    roll
    0.14
     Rolling
    0.14
    滾
    0.13
     rolled
    0.13
    Roll
    0.13
    .roll
    0.13
     Roll
    0.13
    Activations Density 0.058%

    No Known Activations