© 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. 876
    Prev
    Next
    INDEX
    Explanations

    high school athletics and activities

    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
    ingle
    -0.10
    è¶Ł
    -0.09
    uxt
    -0.08
    éĴĪ
    -0.08
    eva
    -0.08
    sWith
    -0.08
    è´´åIJ§
    -0.08
    Ñıн
    -0.08
    åĿļåĽº
    -0.08
     Natur
    -0.08
    POSITIVE LOGITS
    æŁĶ
    0.09
    мÑı
    0.09
    æļ§
    0.09
    mani
    0.08
    èĮĥåĽ´
    0.08
     indefinite
    0.08
    cox
    0.08
    诰
    0.08
    KeyEvent
    0.08
    dims
    0.08
    Activations Density 0.003%

    No Known Activations