© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49946
    Prev
    Next
    INDEX
    Explanations

    final item sequence

    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
    åħ¨éĿ¢åIJ¯åĬ¨
    -0.08
    åłĤ
    -0.07
    轻巧
    -0.07
    itu
    -0.07
    pan
    -0.07
    èIJ©
    -0.07
    asket
    -0.07
    ä¾ĽåºĶ
    -0.07
    ä¸Ĭèħº
    -0.07
     Tec
    -0.06
    POSITIVE LOGITS
    çĨĻ
    0.07
    åŃľ
    0.07
    linie
    0.07
    ä½ľå¥½
    0.07
    ãģĮãģĤãģ£ãģ¦
    0.07
     facing
    0.06
    çĻ½éľ²
    0.06
    wali
    0.06
    elius
    0.06
    linien
    0.06
    Activations Density 0.041%

    No Known Activations