© 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. 47053
    Prev
    Next
    INDEX
    Explanations

    short-term exercise

    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
    ież
    -0.08
    åĴª
    -0.07
    xDD
    -0.07
    ä»ĭ
    -0.07
    åħį
    -0.07
    iore
    -0.07
    iculum
    -0.07
    enne
    -0.07
    大åĵ¥
    -0.07
    _DRIVE
    -0.07
    POSITIVE LOGITS
    ite
    0.08
    çĶ²çŃī
    0.07
    ilton
    0.07
    -parse
    0.06
    agrid
    0.06
    é
    0.06
    ird
    0.06
    ημα
    0.06
    çĶŁæºIJ
    0.06
    /*----------------------------------------------------------------------------
    0.06
    Activations Density 0.404%

    No Known Activations