© 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. 43675
    Prev
    Next
    INDEX
    Explanations

    perpendicular to the direction

    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
    LowerCase
    -0.10
    ölf
    -0.09
    ׼ף
    -0.09
    Ãłs
    -0.09
     sÃłng
    -0.08
    ãģıãĤĬ
    -0.08
    Ñĥди
    -0.08
    .listeners
    -0.08
    adero
    -0.08
    ErrorException
    -0.08
    POSITIVE LOGITS
    æĸ¹åIJij
    0.07
    并ä¸Ķ
    0.07
    umbo
    0.07
    åŀĤ
    0.06
    åŀĤ缴
    0.06
     conver
    0.06
     at
    0.06
    çļĦæĸ¹åIJij
    0.06
     direction
    0.06
     perpendicular
    0.06
    Activations Density 0.003%

    No Known Activations