© 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. 37899
    Prev
    Next
    INDEX
    Explanations

    see below

    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
    æĢ»èĢĮè¨Ģä¹ĭ
    -0.07
    adata
    -0.07
    _warnings
    -0.07
    åīįè¿°
    -0.07
    orra
    -0.07
    browse
    -0.07
    æ´Ĵ
    -0.07
    urier
    -0.06
    ä¸Ĭè¿°
    -0.06
    .mo
    -0.06
    POSITIVE LOGITS
    cher
    0.08
    xmm
    0.07
    ayar
    0.07
    ssen
    0.07
    _ws
    0.07
    isir
    0.07
    裡
    0.06
    еÑĪе
    0.06
    没æ³ķ
    0.06
    çģ«çĥŃçļĦ
    0.06
    Activations Density 0.001%

    No Known Activations