© 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. 3298
    Prev
    Next
    INDEX
    Explanations

    active status, buttons, feature, applied

    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
    TransparentColor
    -0.08
    DialogContent
    -0.08
    浦
    -0.08
    errs
    -0.08
     erotik
    -0.08
    _strerror
    -0.07
    Editors
    -0.07
    æłĩè¯Ĩçłģ
    -0.07
    website
    -0.07
     ÐļÑĢаÑģи
    -0.07
    POSITIVE LOGITS
     {@
    0.08
    é»ĺ认
    0.08
    ril
    0.07
     unset
    0.07
    _NOW
    0.07
     settings
    0.07
     UI
    0.07
    æĽ
    0.07
     Logic
    0.06
     Entity
    0.06
    Activations Density 0.007%

    No Known Activations