© 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. 1272
    Prev
    Next
    INDEX
    Explanations

    uncertainties and questions

    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
    olle
    -0.08
    oland
    -0.07
    å±ħ士
    -0.07
    parcel
    -0.07
    ÙĪÙĦات
    -0.07
    oleh
    -0.07
    /sources
    -0.06
    åħĭåħ°
    -0.06
    oles
    -0.06
    MX
    -0.06
    POSITIVE LOGITS
    éĻ¤éĿŀ
    0.08
    ington
    0.07
    äºĭçļĦ
    0.07
    _callbacks
    0.07
    çİ°å®ŀ
    0.07
    çļĦä¸į
    0.07
    Persistent
    0.07
    çļĦçİ°å®ŀ
    0.07
    对æѤ
    0.07
    å¥½åľ¨
    0.07
    Activations Density 0.023%

    No Known Activations