© 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. 43305
    Prev
    Next
    INDEX
    Explanations

    characteristic cycle

    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
    elat
    -0.07
    .initialize
    -0.07
    porte
    -0.07
    å¹³åı°å»ºè®¾
    -0.07
    _CLUSTER
    -0.07
     Rosenstein
    -0.07
    ลู
    -0.07
    _FETCH
    -0.07
    ghi
    -0.07
    åıĭæĥħéĵ¾æİ¥
    -0.07
    POSITIVE LOGITS
    åIJĦèĩª
    0.10
    åIJĦèĩªçļĦ
    0.08
    åIJĦæľī
    0.08
     individually
    0.08
     masing
    0.07
    个人
    0.07
     representations
    0.06
    代表çļĦ
    0.06
     their
    0.06
     alike
    0.06
    Activations Density 0.082%

    No Known Activations