© 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. 57394
    Prev
    Next
    INDEX
    Explanations

    linkage map

    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
    tring
    -0.08
    _timestamp
    -0.07
    keit
    -0.07
    太ä¸Ĭ
    -0.07
    Timestamp
    -0.07
    çī¹ç§į
    -0.07
    æ³Ħ
    -0.07
    ลำ
    -0.07
     маÑģ
    -0.07
     setObject
    -0.07
    POSITIVE LOGITS
    çĻ¾åĪĨä¹ĭ
    0.07
    pps
    0.07
    _between
    0.07
    elson
    0.07
    äºĴ
    0.07
     (%)
    0.07
     measured
    0.07
     distance
    0.06
     percent
    0.06
    gression
    0.06
    Activations Density 0.002%

    No Known Activations