© 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. 27342
    Prev
    Next
    INDEX
    Explanations

    from, dari, createFrom, 銎, à¸Īาà¸ģ

    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
    对åħ¶è¿Ľè¡Į
    -0.09
    ä¸İä¹ĭ
    -0.09
    iland
    -0.07
    )>>
    -0.07
    踪
    -0.07
    对åħ¶
    -0.07
    令æĪij
    -0.06
    让èĩªå·±
    -0.06
    jong
    -0.06
    为åħ¶
    -0.06
    POSITIVE LOGITS
    มาà¸Īาà¸ģ
    0.10
    缴æİ¥ä»İ
    0.09
     from
    0.09
     dari
    0.09
    .createFrom
    0.09
    åľ°ä»İ
    0.09
     từ
    0.09
    _from
    0.09
    ä¹Łä»İ
    0.09
    à¸Īาà¸ģ
    0.08
    Activations Density 0.348%

    No Known Activations