© 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. 11348
    Prev
    Next
    INDEX
    Explanations

    orthogonal relationships

    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
    æ¡¥åĮº
    -0.08
     optimistic
    -0.07
    azon
    -0.07
     sho
    -0.07
    容éĩıçļĦ
    -0.07
    æ®·
    -0.07
    æĤ²æ¬¢
    -0.07
    Bridge
    -0.07
     elér
    -0.07
    涨
    -0.06
    POSITIVE LOGITS
    åŀĤ缴
    0.10
    pendicular
    0.10
     perpendicular
    0.10
     orthogonal
    0.10
     kese
    0.08
    unan
    0.08
     orth
    0.08
     Orth
    0.08
     âŁ
    0.08
    aat
    0.08
    Activations Density 0.001%

    No Known Activations