© 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. 31670
    Prev
    Next
    INDEX
    Explanations

    college and university

    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
    åĪĿä¸Ń
    -0.11
    ä¸ŃèĢĥ
    -0.09
    å°ıåѦ
    -0.09
    èįļ
    -0.09
    asin
    -0.09
    åĩŃ
    -0.09
    çľģæķĻèĤ²åİħ
    -0.08
    æģĴ
    -0.08
    _Copy
    -0.08
    èĤ²äºº
    -0.08
    POSITIVE LOGITS
    ä¸ī大
    0.09
    åĽĽå¤§
    0.09
    èµī
    0.08
     Lyons
    0.08
    ç³ľ
    0.08
     fur
    0.08
    Trivia
    0.08
    ORK
    0.08
    è¾¹ç¼ĺ
    0.08
    åķĦ
    0.08
    Activations Density 0.096%

    No Known Activations