© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48003
    Prev
    Next
    INDEX
    Explanations

    book genre label

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovac
    -0.07
    çļĦä¸ĢäºĽ
    -0.07
    å¼Ĥ常æĥħåĨµ
    -0.07
    ס×Ļ
    -0.07
    itz
    -0.07
     meanwhile
    -0.07
     alternatively
    -0.07
     accordingly
    -0.06
    >Note
    -0.06
    netz
    -0.06
    POSITIVE LOGITS
     âľĶ
    0.08
    éĺ¿æĭī伯
    0.07
    ADED
    0.07
    ä¸ĢèĪ¬ä¸º
    0.07
    ä¸ĢèĪ¬æĺ¯
    0.07
    åĬłæĭ¿å¤§
    0.07
    Ùĭ
    0.06
    ÑĤÑİ
    0.06
    iswa
    0.06
    SUMER
    0.06
    Activations Density 0.004%

    No Known Activations