© 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. 12611
    Prev
    Next
    INDEX
    Explanations

    stats _src

    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
    assi
    -0.08
    leit
    -0.08
    urgi
    -0.08
    _ABI
    -0.08
    缸éĢ¢
    -0.08
    /logging
    -0.07
    iest
    -0.07
    bod
    -0.07
    assa
    -0.07
    UrlParser
    -0.07
    POSITIVE LOGITS
    åĬĿ
    0.07
    èµŀ
    0.07
    润
    0.07
     Kou
    0.06
     Hi
    0.06
    áĥĻ
    0.06
    ãĥ¼ãĥ«
    0.06
    éĶĻçļĦ
    0.06
     اÙĦÙĤÙħر
    0.06
     errone
    0.06
    Activations Density 0.206%

    No Known Activations