© 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. 50933
    Prev
    Next
    INDEX
    Explanations

    middle, center, vertical position

    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
    assi
    -0.08
    aki
    -0.08
    icolor
    -0.07
    åĴ¨
    -0.07
    ê°ģ
    -0.07
    اتÙĬ
    -0.07
    ,input
    -0.07
     direct
    -0.07
    زÙħ
    -0.07
    _SIM
    -0.07
    POSITIVE LOGITS
     midway
    0.14
     midpoint
    0.14
     middle
    0.13
    middle
    0.13
    Middle
    0.12
     Middle
    0.12
    ä¸ŃéĹ´
    0.12
    mid
    0.12
     ÙĪسط
    0.11
    ä¸Ń庸
    0.11
    Activations Density 0.042%

    No Known Activations