© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35714
    Prev
    Next
    INDEX
    Explanations

    football players

    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
    çĶ³
    -0.09
    æ¿ł
    -0.09
    asaki
    -0.09
    aurus
    -0.09
    assen
    -0.09
    ä¸įå¾Ĺä¸į说
    -0.09
    巴士
    -0.08
    _BUF
    -0.08
    enga
    -0.08
    amac
    -0.08
    POSITIVE LOGITS
    ä½ľèĢħæīĢæľī
    0.08
    大å§IJ
    0.08
    ÑĮе
    0.08
    çļĦåİĭåĬĽ
    0.08
    满满
    0.08
    thed
    0.08
    满äºĨ
    0.08
    åĩºåĽ½çķĻåѦ
    0.08
    åĴĮ个人
    0.08
    仨
    0.08
    Activations Density 0.871%

    No Known Activations