© 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. 61584
    Prev
    Next
    INDEX
    Explanations

    crystal display, recording, bonding

    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
    ÚĨار
    -0.07
    å°ıåĪ°
    -0.07
    eil
    -0.07
    åıĬåĪ©æģ¯
    -0.07
    åĩ«
    -0.07
    feb
    -0.07
    cono
    -0.06
    ãģĨãģĪ
    -0.06
    åĿļæĮģ
    -0.06
    ç¿İ
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.12
    çŃīä¼łç»Ł
    0.08
     thuần
    0.08
     наобоÑĢоÑĤ
    0.08
    缸æ¯Ķä¹ĭä¸ĭ
    0.07
    åIJİèĢħ
    0.07
     counterpart
    0.07
    ä¸Ń转
    0.07
    ause
    0.07
    ular
    0.07
    Activations Density 0.198%

    No Known Activations