© 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. 14494
    Prev
    Next
    INDEX
    Explanations

    son of

    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
    রা
    -0.07
    perate
    -0.07
    åĨħå®¹è¿Ľè¡Į
    -0.06
    (T
    -0.06
    åĨħ容æľī
    -0.06
    Ñİн
    -0.06
    åIJijèį£
    -0.06
    æľīäººåľ¨
    -0.06
    Ỽ
    -0.06
    /plugin
    -0.06
    POSITIVE LOGITS
    第ä¸Ģ代
    0.08
    åłĤåłĤ
    0.08
    unc
    0.07
    åıŃ
    0.07
    icult
    0.07
    第ä¸ī代
    0.07
    celli
    0.07
     parents
    0.07
    apa
    0.07
    ystone
    0.07
    Activations Density 0.331%

    No Known Activations