© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30409
    Prev
    Next
    INDEX
    Explanations

    angle, degrees, radians, tilt

    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
     cycle
    -0.07
    æĹ¶æľŁçļĦ
    -0.07
    ocide
    -0.07
    -cycle
    -0.07
    cycle
    -0.06
    Cycle
    -0.06
    impse
    -0.06
     chu
    -0.06
    haps
    -0.06
     Cycle
    -0.06
    POSITIVE LOGITS
    伶
    0.08
    çľ¼çķĮ
    0.08
     radians
    0.08
    ubar
    0.08
     angles
    0.08
    弧度
    0.08
    éĻIJ
    0.08
    -angle
    0.08
     ReturnType
    0.08
    angles
    0.08
    Activations Density 0.003%

    No Known Activations