© 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. 18155
    Prev
    Next
    INDEX
    Explanations

    command line arguments, values, numbers, code syntax

    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
    лÑİÑĤ
    -0.07
    çĭ¬åįł
    -0.07
    oday
    -0.07
    çĬ¯
    -0.07
    .ut
    -0.07
    maken
    -0.07
    èĬĿ
    -0.06
    ç§ij
    -0.06
    èĬ¥
    -0.06
    isse
    -0.06
    POSITIVE LOGITS
    /../
    0.08
    oulos
    0.07
    oggio
    0.07
    برا
    0.07
    umm
    0.07
    è¿Ľåħ¥åĪ°
    0.07
    оÑģÑĤо
    0.07
    ાય
    0.06
    ิม
    0.06
    è¿ĽåĪ°
    0.06
    Activations Density 0.042%

    No Known Activations