© 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. 9948
    Prev
    Next
    INDEX
    Explanations

    URLs and code delimiters

    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
    oll
    -0.07
    å·¨é¢Ŀ
    -0.06
    æ¶Į
    -0.06
    ecam
    -0.06
    _Abstract
    -0.06
    ako
    -0.06
    ock
    -0.06
    wcs
    -0.06
    çī¢åĽºæłijç«ĭ
    -0.06
    转æį¢ä¸º
    -0.06
    POSITIVE LOGITS
    ymar
    0.09
    ä¾łä¼ł
    0.08
    纵
    0.08
    縱
    0.08
    icina
    0.08
    пÑı
    0.08
    itaciones
    0.07
    меÑĤи
    0.07
    decision
    0.07
    uples
    0.07
    Activations Density 0.023%

    No Known Activations