© 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. 62067
    Prev
    Next
    INDEX
    Explanations

    parenthetical terms

    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
     Hend
    -0.06
    äºļ太
    -0.06
     Grand
    -0.06
     Based
    -0.06
    æķĻä½łå¦Ĥä½ķ
    -0.06
     based
    -0.06
    idou
    -0.06
     Kil
    -0.06
     Fort
    -0.06
    èĩ¼
    -0.06
    POSITIVE LOGITS
    nado
    0.07
     Caucus
    0.07
     Ellison
    0.07
    rone
    0.07
    å±ķå¼Ģåħ¨æĸĩ
    0.07
    озна
    0.07
    żu
    0.07
    पà¥ģर
    0.07
     SEEK
    0.07
    imaan
    0.07
    Activations Density 0.066%

    No Known Activations