© 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. 12136
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and variables

    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
    림
    -0.07
    jec
    -0.07
    omy
    -0.07
    itto
    -0.07
    omnia
    -0.07
    nox
    -0.07
    élection
    -0.07
    纷纷
    -0.06
    uros
    -0.06
    anke
    -0.06
    POSITIVE LOGITS
    +
    0.11
     плÑİÑģ
    0.10
    +S
    0.09
     plus
    0.09
    -plus
    0.09
    åĬł
    0.09
     cá»Ļng
    0.08
    +i
    0.08
    ï¼ĭ
    0.08
    +\
    0.08
    Activations Density 0.005%

    No Known Activations