© 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. 47034
    Prev
    Next
    INDEX
    Explanations

    table separators

    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
    adem
    -0.08
    管çIJĨæľīéĻIJåħ¬åı¸
    -0.07
    管çIJĨå§Ķåijĺä¼ļ
    -0.07
     Ñģло
    -0.07
    åħ¶æŀĹ
    -0.07
    ën
    -0.07
    pati
    -0.07
    åįĹåĽ½
    -0.07
    akup
    -0.07
    lick
    -0.07
    POSITIVE LOGITS
    ÑģÑĤÑĢ
    0.07
    imony
    0.07
    nten
    0.06
    áĥĴáĥĺ
    0.06
    ردد
    0.06
    ëĿ½
    0.06
    μοÏħ
    0.06
    æ¸ħ空
    0.06
    ivals
    0.06
    ãģ¤ãģı
    0.06
    Activations Density 0.012%

    No Known Activations