© 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. 47225
    Prev
    Next
    INDEX
    Explanations

    is followed by foreign characters or 'Meth', 'the', 'My'

    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
    ине
    -0.07
    .br
    -0.07
    èµĦæĸĻä¸ĭè½½
    -0.07
    userinfo
    -0.07
    ино
    -0.07
    داÙĨ
    -0.07
    åĪĨå¤ĸ
    -0.07
    irman
    -0.07
    .AP
    -0.07
    aeda
    -0.07
    POSITIVE LOGITS
    oland
    0.07
    ziem
    0.07
    оÑĤоÑĢ
    0.07
    æ¦ľ
    0.07
    å¦Ļ
    0.06
    abin
    0.06
    ìłĢ
    0.06
    æ±łä¸Ń
    0.06
    éĵ¸
    0.06
     кандид
    0.06
    Activations Density 0.042%

    No Known Activations