© 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. 11347
    Prev
    Next
    INDEX
    Explanations

    bone cancer, weekly recurrence, dumping position

    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
    =view
    -0.07
    泡
    -0.06
    ”—
    -0.06
    teman
    -0.06
    级以ä¸Ĭ
    -0.06
    å¤ļ头
    -0.06
    ivr
    -0.06
    inqui
    -0.06
    ãĢģãĢģ
    -0.06
    stands
    -0.06
    POSITIVE LOGITS
    pton
    0.08
    ãĤĴ表
    0.08
    _IND
    0.08
    è²Į
    0.08
    èµ·è§ģ
    0.07
    ç´
    0.07
    _raw
    0.07
    onas
    0.07
    uw
    0.07
    ä¹Łæľī人
    0.07
    Activations Density 0.095%

    No Known Activations