© 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. 49480
    Prev
    Next
    INDEX
    Explanations

    cube shapes

    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
    _pixels
    -0.09
    å¹ħ
    -0.09
    Ùħز
    -0.08
    éī´
    -0.08
    Lane
    -0.08
    åľĨåľĪ
    -0.08
     lane
    -0.08
    stripe
    -0.08
    çijľ
    -0.08
     baud
    -0.08
    POSITIVE LOGITS
     cube
    0.12
    ç«ĭæĸ¹
    0.12
    Cube
    0.12
    cube
    0.11
     Cube
    0.11
     cubes
    0.11
    xyz
    0.11
     cub
    0.10
    (cube
    0.10
    ä½ĵ积
    0.10
    Activations Density 0.014%

    No Known Activations