© 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. 63720
    Prev
    Next
    INDEX
    Explanations

    agent or agents

    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
    ings
    -0.10
    ness
    -0.10
    ish
    -0.08
     ìĿ¸íķ´
    -0.08
    shire
    -0.08
    ient
    -0.07
    ington
    -0.07
    üren
    -0.07
    INGS
    -0.07
    ynn
    -0.07
    POSITIVE LOGITS
    ourney
    0.09
    UnderTest
    0.09
    zelfde
    0.09
    allah
    0.09
    leman
    0.09
    ielle
    0.09
    -produ
    0.08
    yal
    0.08
    bower
    0.08
    stvÃŃ
    0.08
    Activations Density 0.032%

    No Known Activations