© 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. 44062
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
    é¨İ士
    -0.07
    SelectedItem
    -0.07
    è¿Ļä¹Ł
    -0.06
    ÑĦоÑĢ
    -0.06
    iever
    -0.06
     sekel
    -0.06
    _INCREMENT
    -0.06
    _LEG
    -0.06
    eted
    -0.06
    itik
    -0.06
    POSITIVE LOGITS
    caffold
    0.08
    ĸ
    0.07
    éĢģä½ł
    0.07
    ocen
    0.07
    gris
    0.07
    æĸ¤
    0.06
    nyder
    0.06
    DCALL
    0.06
    æŁ¥çľĭåħ¨éĥ¨
    0.06
    ÙħاÙĨØ©
    0.06
    Activations Density 0.002%

    No Known Activations