© 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. 13054
    Prev
    Next
    INDEX
    Explanations

    optical component or network device

    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
    اÙĨس
    -0.08
    enang
    -0.08
    循çĴ°
    -0.08
     leo
    -0.08
    åĽ¢åijĺ
    -0.07
    .rmi
    -0.07
    -highlight
    -0.07
    ãĥ¼ãĤ¸
    -0.07
    举æĿ¯
    -0.07
    unden
    -0.07
    POSITIVE LOGITS
     boundary
    0.07
     midpoint
    0.07
     boundaries
    0.07
    ÑĢаниÑĨ
    0.07
     separating
    0.06
    è¾¹çķĮ
    0.06
    åħ¬ä¿¡
    0.06
     اÙĦØŃدÙĪد
    0.06
     deflect
    0.06
    å¤ĦåĪĨ
    0.06
    Activations Density 0.002%

    No Known Activations