© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 3022
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    å¯ĵ
    -0.08
    _parms
    -0.07
    æłª
    -0.07
    cury
    -0.07
    线æĿIJ
    -0.07
    emm
    -0.07
     random
    -0.07
    ÙĬست
    -0.07
    ystick
    -0.07
    krim
    -0.07
    POSITIVE LOGITS
     patches
    0.10
     patch
    0.09
    patches
    0.09
     overlaps
    0.08
    _coverage
    0.08
    patch
    0.08
    refs
    0.08
    ref
    0.08
     Patch
    0.07
    è¦ĨçĽĸ
    0.07
    Activations Density 0.008%

    No Known Activations