© 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. 10512
    Prev
    Next
    INDEX
    Explanations

    dispositions of the Fourth Circuit

    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
     Rum
    -0.07
    edom
    -0.07
    è¯ŃéŁ³æŶéķ¿
    -0.07
    ترÙĪÙĨ
    -0.06
    ÑĤÑģÑı
    -0.06
      ↵
    -0.06
    _native
    -0.06
    sey
    -0.06
    [...]
    -0.06
    )**,
    -0.06
    POSITIVE LOGITS
    çŁ¥ãĤī
    0.08
    .".
    0.07
    awi
    0.07
    meister
    0.07
    >.</
    0.07
     newPos
    0.07
    ãĢĤï¼ī
    0.06
    లి
    0.06
    æŶ任
    0.06
    URING
    0.06
    Activations Density 0.770%

    No Known Activations