© 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. 44080
    Prev
    Next
    INDEX
    Explanations

    angle, degrees, inclination

    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
    سÙģ
    -0.07
     ÎłÏģÏĮ
    -0.07
    umba
    -0.07
    Ø´ÙĬر
    -0.07
    tone
    -0.07
    .isNull
    -0.07
     xô
    -0.06
    ä¸ĩå¹´
    -0.06
    меÑĢа
    -0.06
    容éĩıçļĦ
    -0.06
    POSITIVE LOGITS
     angle
    0.10
     angles
    0.10
    è§Ĵ
    0.09
     incl
    0.08
    angle
    0.08
     inclination
    0.08
    angled
    0.08
    è§Ĵ度
    0.08
     Angle
    0.08
     angled
    0.08
    Activations Density 0.010%

    No Known Activations