© 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. 20031
    Prev
    Next
    INDEX
    Explanations

    enterprise devices

    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
    fos
    -0.07
    berger
    -0.07
    åĴĮå·¥ä½ľ
    -0.07
    czyn
    -0.06
    ä¸Ģå¤ľ
    -0.06
    ëł¹
    -0.06
    ikas
    -0.06
    _metrics
    -0.06
    аÑĤÑĥ
    -0.06
    極
    -0.06
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.08
     rather
    0.07
     ag
    0.07
    hurst
    0.07
    hun
    0.07
    è·¯éĢı
    0.07
    icy
    0.07
    izarre
    0.07
    rather
    0.06
    èĢĮä¸įæĺ¯
    0.06
    Activations Density 0.034%

    No Known Activations