© 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. 42196
    Prev
    Next
    INDEX
    Explanations

    angle degrees measure

    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
    ä½ĵ积
    -0.07
    NEY
    -0.07
    ืà¸Ń
    -0.07
    è§ģ人
    -0.07
    çī©è´¨çļĦ
    -0.07
     subs
    -0.07
    жа
    -0.07
    éĩıåĬĽ
    -0.07
    eyJ
    -0.07
    XXXXXXXX
    -0.07
    POSITIVE LOGITS
     angles
    0.08
    çĿ¦
    0.08
    wai
    0.07
     interior
    0.07
     Ñĥгла
    0.07
     sung
    0.07
    ä¸Ģè§Ĵ
    0.07
     acute
    0.07
     angle
    0.07
    Angle
    0.07
    Activations Density 0.001%

    No Known Activations