© 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. 42739
    Prev
    Next
    INDEX
    Explanations

    data, this, given, code, or law

    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
    ation
    -0.10
    aji
    -0.09
    ality
    -0.08
    æĸ°åĬłåĿ¡
    -0.07
    寥
    -0.07
    elj
    -0.07
    äºĽè®¸
    -0.07
    nade
    -0.06
    ter
    -0.06
    ¹
    -0.06
    POSITIVE LOGITS
    zelfde
    0.12
    oop
    0.10
    erness
    0.09
    entifier
    0.08
    sWith
    0.08
    oretical
    0.08
    ories
    0.08
    ement
    0.08
    roud
    0.08
    ë¦Ħ
    0.08
    Activations Density 0.003%

    No Known Activations