© 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. 9218
    Prev
    Next
    INDEX
    Explanations

    diode

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.13
    ãĤĪãģĨãģª
    -0.11
    ness
    -0.10
    nt
    -0.09
    缸è¾ħ缸æĪIJ
    -0.08
    nya
    -0.08
    abouts
    -0.08
    ãģ¹ãģį
    -0.08
    ipt
    -0.08
    ÏĤ
    -0.08
    POSITIVE LOGITS
    zelfde
    0.14
    urnal
    0.10
    wajibkan
    0.09
    SSERT
    0.09
    ction
    0.08
    agher
    0.08
    plom
    0.08
    몬ëĵľ
    0.08
    acus
    0.08
    erweise
    0.08
    Activations Density 0.070%

    No Known Activations