© 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. 38158
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    ister
    -0.07
    onger
    -0.07
    éIJĺ
    -0.07
    croft
    -0.07
    CLU
    -0.07
    -chief
    -0.06
    _WATCH
    -0.06
    è§Ħ
    -0.06
    angnya
    -0.06
    utin
    -0.06
    POSITIVE LOGITS
    æļĤå®ļ
    0.07
    еÑģе
    0.06
    ewe
    0.06
    她æīį
    0.06
    åĸľè¿İ
    0.06
    roduzione
    0.06
    åijµ
    0.06
    ÑĸÑĢ
    0.06
    åįķ项éĢīæĭ©é¢ĺ
    0.06
    irut
    0.06
    Activations Density 0.006%

    No Known Activations