© 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. 47485
    Prev
    Next
    INDEX
    Explanations

    appellant, appellee, names

    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
    emt
    -0.07
    滨æ¹ĸ
    -0.06
    åħ·ä½ĵå¦Ĥä¸ĭ
    -0.06
    elts
    -0.06
    iffs
    -0.06
     Contributors
    -0.06
    lew
    -0.06
    beg
    -0.06
     [~,
    -0.06
    igni
    -0.06
    POSITIVE LOGITS
    å¦Ĥä¸Ĭ
    0.08
    ryptography
    0.07
    okok
    0.07
    ä¸Ĭè¨ĺ
    0.07
    ä¸Ĭæĸĩ
    0.07
    ä¸ĬåĽ¾
    0.07
    aney
    0.07
    plevel
    0.07
    æ°Ľ
    0.07
    ','',
    0.07
    Activations Density 0.416%

    No Known Activations