© 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. 20766
    Prev
    Next
    INDEX
    Explanations

    Chris Ber

    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
    涯
    -0.07
    å¿ĥçĹĽ
    -0.07
     Vortrag
    -0.07
    ãĥ¡ãĥª
    -0.06
    对å¾ħ
    -0.06
    è¦ģçŁ¥éģĵ
    -0.06
    åľĨæĺİ
    -0.06
    çĮ¾
    -0.06
    åIJİ天
    -0.06
    adh
    -0.06
    POSITIVE LOGITS
     ës
    0.08
    udir
    0.08
    _INITIALIZER
    0.07
    į°
    0.07
    åĪĽä¼ĺ
    0.07
    éĸī
    0.07
    ë°Ģ
    0.07
    igneur
    0.07
    EIC
    0.07
    cancel
    0.06
    Activations Density 0.001%

    No Known Activations