© 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. 23809
    Prev
    Next
    INDEX
    Explanations

    code termination semicolon

    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
    ctu
    -0.07
    rain
    -0.07
    ()",
    -0.07
    kün
    -0.07
    cue
    -0.07
    iq
    -0.07
    nowled
    -0.07
    otlin
    -0.07
    年以ä¸ĭ
    -0.07
    })",
    -0.07
    POSITIVE LOGITS
    ì¹Ļ
    0.07
    uta
    0.06
    ÏĨεÏģ
    0.06
     obv
    0.06
    ä¸įå¼Ģ
    0.06
     vant
    0.06
    ieras
    0.06
    oreal
    0.06
    apul
    0.06
    èijĨ
    0.06
    Activations Density 0.001%

    No Known Activations