© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15998
    Prev
    Next
    INDEX
    Explanations

    listing collaborators or features

    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
    reation
    -0.07
    mack
    -0.07
    çİĭæ°ı
    -0.07
    jang
    -0.06
    PU
    -0.06
    tire
    -0.06
    éĢĨ
    -0.06
    urd
    -0.06
    å¦ĤæѤ
    -0.06
    çŁ¥éģĵèĩªå·±çļĦ
    -0.06
    POSITIVE LOGITS
    ÎŃÏģ
    0.08
    apul
    0.08
    ernel
    0.07
    ä¸Ģå¸Ĩ
    0.07
    åı¯æ¢¦
    0.07
    HostName
    0.07
    åħ¨é«Ķ
    0.07
    اÙĦتÙĩا
    0.07
    åħ¨ä½ĵ人åijĺ
    0.07
    ÄĻd
    0.07
    Activations Density 0.075%

    No Known Activations