© 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. 43670
    Prev
    Next
    INDEX
    Explanations

    \int, f, \langle

    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
    ena
    -0.07
    –
    -0.07
    ingen
    -0.07
    маÑĢа
    -0.06
    gie
    -0.06
    kampf
    -0.06
    rud
    -0.06
    .IsSuccess
    -0.06
     PREFIX
    -0.06
    /top
    -0.06
    POSITIVE LOGITS
    ystate
    0.08
     Trinh
    0.07
    身临åħ¶å¢ĥ
    0.07
     ôt
    0.07
    ench
    0.07
     Dix
    0.06
    ä¸ĩå¥Ĺ
    0.06
    ä¹ĭåĴĮ
    0.06
    _scal
    0.06
    ç±³å¤Ħ
    0.06
    Activations Density 0.006%

    No Known Activations