© 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. 22339
    Prev
    Next
    INDEX
    Explanations

    mount/dismount, encrypt/decrypt, locking/unlocking

    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
     fix
    -0.06
    ys
    -0.06
     Wald
    -0.06
    _hd
    -0.06
    æĥħåĨµ
    -0.06
    irectory
    -0.06
    è¿ŀäºij
    -0.06
    çľ
    -0.06
     صاÙĦØŃ
    -0.06
     dou
    -0.06
    POSITIVE LOGITS
    åıįä¹ĭ
    0.14
    /from
    0.12
    åıįè¿ĩæĿ¥
    0.12
     Conversely
    0.11
     revers
    0.11
    åĴĮ解
    0.11
     reversible
    0.11
     vice
    0.11
    éĢĨãģ«
    0.10
    缸åıįçļĦ
    0.10
    Activations Density 0.715%

    No Known Activations