© 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. 8642
    Prev
    Next
    INDEX
    Explanations

    is followed by descriptive phrases

    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
    éĢļ
    -0.08
    веÑĢÑı
    -0.08
    лиÑģ
    -0.07
    ¿
    -0.07
    .off
    -0.07
    ánh
    -0.07
    -caret
    -0.07
    enty
    -0.07
    仲
    -0.07
    ServerError
    -0.07
    POSITIVE LOGITS
    YY
    0.08
    _unused
    0.07
    ä¸İä¼łç»Ł
    0.07
    æĬĵåĪ°
    0.07
    ä»İä¸ļ
    0.07
    æľ¬çıŃ
    0.07
     Ø£ÙĪÙĦÙī
    0.06
    ÑĢÑĥз
    0.06
    /native
    0.06
    åħ¨èĥľ
    0.06
    Activations Density 0.001%

    No Known Activations