© 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. 22150
    Prev
    Next
    INDEX
    Explanations

    (99m)Tc

    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
    عر
    -0.08
    iid
    -0.08
    iet
    -0.07
     unint
    -0.07
    etat
    -0.07
    ληÏĤ
    -0.07
    æĭĿ
    -0.06
    æıIJä¾Ľæĸ¹
    -0.06
    ievo
    -0.06
    ULO
    -0.06
    POSITIVE LOGITS
    ofday
    0.07
    ׼×Ļ
    0.07
    inking
    0.07
    оÑĢа
    0.07
    éŁ³
    0.07
    gress
    0.07
    æĪIJçīĩ
    0.07
    _DECLARE
    0.07
    ough
    0.07
    codec
    0.07
    Activations Density 0.002%

    No Known Activations