© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4375
    Prev
    Next
    INDEX
    Explanations

    sports statistics and records

    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
     pare
    -0.09
    亥
    -0.08
     cou
    -0.08
    ä¾Ŀ次
    -0.08
    Https
    -0.08
    ucid
    -0.08
    preg
    -0.07
    _UNITS
    -0.07
    CHA
    -0.07
     Bout
    -0.07
    POSITIVE LOGITS
    èī¯å¥½
    0.10
    èī¯å¥½çļĦ
    0.10
    ìľ¨
    0.09
    è¾ĥé«ĺçļĦ
    0.09
    ç¼ĺ
    0.09
    ratio
    0.09
    ä¸Ĭåįĩ
    0.09
    è¾ĥä½İ
    0.09
    ç·£
    0.09
    è¾ĥ好çļĦ
    0.09
    Activations Density 0.010%

    No Known Activations