© 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. 47229
    Prev
    Next
    INDEX
    Explanations

    safe

    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
    zelf
    -0.10
    ather
    -0.09
    naire
    -0.09
    IgnoreCase
    -0.08
    ÙĬاÙĨ
    -0.08
    æł·çļĦ
    -0.08
    åĭĥåĭĥ
    -0.08
    egen
    -0.08
    ä¸įä¼ij
    -0.07
    acier
    -0.07
    POSITIVE LOGITS
    èµ·è§ģ
    0.13
    heits
    0.10
    lest
    0.09
    -looking
    0.08
    zustellen
    0.08
    keeping
    0.08
    -ish
    0.08
    keepers
    0.08
    AreaView
    0.08
    æĹłæ¯Ĵ
    0.08
    Activations Density 0.031%

    No Known Activations