© 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. 22223
    Prev
    Next
    INDEX
    Explanations

    numbers in scientific notation

    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
    erea
    -0.07
    ells
    -0.07
    eira
    -0.06
    èĢ¿èĢ¿
    -0.06
    -team
    -0.06
    rome
    -0.06
    ÙĤÙī
    -0.06
    pane
    -0.06
    çij¶
    -0.06
     Son
    -0.06
    POSITIVE LOGITS
    æĽĻ
    0.08
    isie
    0.08
    ä¹ĭ以
    0.07
    zol
    0.07
    .sup
    0.07
    润åıij
    0.07
    .gov
    0.07
    ستÙĨ
    0.07
    akai
    0.07
    <|fim_prefix|>
    0.07
    Activations Density 0.010%

    No Known Activations