© 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. 16399
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    szcz
    -0.10
    <|box_end|>
    -0.10
    OrElse
    -0.10
    并èĮĤ
    -0.10
    ìį¨
    -0.10
    acon
    -0.10
    ï¸İ
    -0.10
    -0.10
    agger
    -0.10
    翼翼
    -0.09
    POSITIVE LOGITS
    er
    0.10
    (s
    0.08
    al
    0.07
    ìĶ©
    0.07
    i
    0.07
    ized
    0.06
    ÙĬ
    0.06
    ĸ
    0.06
    fuÃŁ
    0.06
    ly
    0.06
    Activations Density 0.085%

    No Known Activations