© 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. 9193
    Prev
    Next
    INDEX
    Explanations

    light source direction and angle

    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
    ìĪł
    -0.07
    åľ¨åĨħ
    -0.07
    alsa
    -0.07
    /y
    -0.07
     waiting
    -0.07
     подлежаÑĤ
    -0.07
    大åĪĢ
    -0.07
    ê²Ģ
    -0.06
    çĽ¼
    -0.06
    以å¾ħ
    -0.06
    POSITIVE LOGITS
     angles
    0.10
    æºIJ
    0.09
    -source
    0.09
     sources
    0.09
     angled
    0.09
     getSource
    0.08
     source
    0.08
     Source
    0.08
     angle
    0.08
    _direction
    0.08
    Activations Density 0.023%

    No Known Activations