© 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. 58538
    Prev
    Next
    INDEX
    Explanations

    cache

    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
    æ¥ļæ¥ļ
    -0.07
    angled
    -0.07
    acus
    -0.07
    غÙħ
    -0.07
    isbury
    -0.07
     tá»ij
    -0.06
    anza
    -0.06
     cuer
    -0.06
    zens
    -0.06
    ä¸įè´¥
    -0.06
    POSITIVE LOGITS
    é¾Ħ
    0.10
    /cache
    0.09
    iry
    0.08
    buster
    0.08
    åĪĩãĤĮ
    0.08
    ufe
    0.07
    orage
    0.07
    edImage
    0.07
    thinkable
    0.07
    æľŁåĨħ
    0.07
    Activations Density 0.059%

    No Known Activations