© 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. 19983
    Prev
    Next
    INDEX
    Explanations

    theoretical formulas (equations)

    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
    临éŨ
    -0.08
     anonym
    -0.07
    åįĥæĸ¹
    -0.07
    achel
    -0.07
    roman
    -0.07
    erei
    -0.06
    è°Īä¸įä¸Ĭ
    -0.06
    andinav
    -0.06
    èm
    -0.06
    anzi
    -0.06
    POSITIVE LOGITS
    计ç®Ĺåħ¬å¼ı
    0.08
     hông
    0.07
    _mgr
    0.07
    าว
    0.07
    ä¸Ń央财æĶ¿
    0.07
     formula
    0.07
     theoret
    0.07
    (eq
    0.07
     theoretical
    0.07
     Formula
    0.07
    Activations Density 0.027%

    No Known Activations