© 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. 62575
    Prev
    Next
    INDEX
    Explanations

    Sort order, increasing or decreasing

    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
    yron
    -0.07
    ÐĹо
    -0.07
    _FALL
    -0.07
     ëį
    -0.07
    adah
    -0.07
    åħ¨éĻ¢
    -0.07
    ä¸ĭéĻįåĪ°
    -0.06
     pageable
    -0.06
    horn
    -0.06
    ables
    -0.06
    POSITIVE LOGITS
    -separated
    0.07
     chắn
    0.07
    tty
    0.07
    ä½įç½®
    0.07
     arrangement
    0.07
    æĻ©
    0.07
    ä¸ŃéĹ´çļĦ
    0.07
    lies
    0.07
    elper
    0.07
    ä¸ŃéĹ´
    0.06
    Activations Density 0.001%

    No Known Activations