© 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. 13790
    Prev
    Next
    INDEX
    Explanations

    crystallographic axes or crystal properties

    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
    è½¼
    -0.08
    ãĥ¼ãĤº
    -0.08
    éĢĹçķĻ
    -0.07
    cese
    -0.07
     thirsty
    -0.07
    antil
    -0.07
    yim
    -0.06
    DataManager
    -0.06
    ayed
    -0.06
    اش
    -0.06
    POSITIVE LOGITS
     orthogonal
    0.08
     lengths
    0.07
     stretches
    0.07
     Crystal
    0.07
    å¸Ĥæĸ°
    0.07
     Trio
    0.07
    缩çŁŃ
    0.07
    缩çŁŃäºĨ
    0.07
     perpendicular
    0.07
    agonal
    0.07
    Activations Density 0.005%

    No Known Activations