© 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. 55795
    Prev
    Next
    INDEX
    Explanations

    oxidized, electric energy, natural tooth, organ culture, Number, CoinEx

    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
    ารี
    -0.07
    é¶
    -0.07
    ë§Į
    -0.06
    宿
    -0.06
    묵
    -0.06
    æıĴ
    -0.06
    å¾·å°Ķ
    -0.06
    .charCodeAt
    -0.06
    ãģĹãĤī
    -0.06
    鸥
    -0.06
    POSITIVE LOGITS
    landers
    0.08
    cec
    0.07
    åī¯çIJĨäºĭéķ¿
    0.07
    à¹Ħà¸Ľà¹Ħà¸Ķà¹ī
    0.07
     Vitt
    0.07
    بÙĬØ©
    0.07
    æĬĬ好
    0.07
    alice
    0.06
    engers
    0.06
     cỡ
    0.06
    Activations Density 0.315%

    No Known Activations