© 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. 13051
    Prev
    Next
    INDEX
    Explanations

    end of sentence markers

    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
    atsu
    -0.08
    æѤç§į
    -0.07
    æŃ£æĺ¯åĽłä¸º
    -0.07
    第åįģå±Ĭ
    -0.07
    åľ¨éĤ£ä¸ª
    -0.07
    inger
    -0.07
    ä¸Ĭè¿°äºĭå®ŀ
    -0.07
    lew
    -0.07
    AGR
    -0.07
    án
    -0.07
    POSITIVE LOGITS
    FORMAT
    0.07
    ä¸įçĪ½
    0.07
    )(*
    0.07
    prim
    0.07
    ahoma
    0.07
    urie
    0.06
    ERAH
    0.06
    ÑĥÑĤа
    0.06
    ems
    0.06
    以ä¸ĭæŃ¥éª¤
    0.06
    Activations Density 0.329%

    No Known Activations