© 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. 28990
    Prev
    Next
    INDEX
    Explanations

    printing output statements

    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
    usic
    -0.08
    riv
    -0.07
    éħĿ
    -0.07
    åı¦ä¸ĢåįĬ
    -0.07
    Ø«
    -0.07
    opan
    -0.07
    ãģ¯ãĤĵ
    -0.06
    otan
    -0.06
    embra
    -0.06
    åħ¨åħļ
    -0.06
    POSITIVE LOGITS
    apter
    0.07
    evoli
    0.07
    _OBJC
    0.07
    ianti
    0.07
    itarian
    0.07
    wiek
    0.07
    彩éĴ¢
    0.07
    è¶ħæłĩ
    0.07
    éĺµ
    0.07
    hiba
    0.07
    Activations Density 0.076%

    No Known Activations