© 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. 7370
    Prev
    Next
    INDEX
    Explanations

    etc. and domain names

    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
    endoza
    -0.08
    pter
    -0.08
    bst
    -0.08
    ìķĻ
    -0.08
    örde
    -0.07
     concretamente
    -0.07
    hle
    -0.07
    unger
    -0.07
    åIJĮå¿Ĺä¸ºæł¸å¿ĥçļĦåħļä¸Ń央
    -0.07
     Constru
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.08
    ï¸ı
    0.08
    å¤ļæĸ¹éĿ¢
    0.07
    osate
    0.07
    SPATH
    0.07
    å¤ļæĸ¹éĿ¢çļĦ
    0.07
    ueux
    0.07
    erb
    0.07
    eri
    0.07
    forgettable
    0.06
    Activations Density 0.001%

    No Known Activations