© 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. 18988
    Prev
    Next
    INDEX
    Explanations

    framing task, subject, problem, or question

    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
    vény
    -0.07
    åħ¬åŃĻ
    -0.07
    arrow
    -0.07
    åĪ°æŶåĢĻ
    -0.06
    æİ¥çĿĢ
    -0.06
    برا
    -0.06
    ustos
    -0.06
    éĩĮäºļ
    -0.06
    XA
    -0.06
     déro
    -0.06
    POSITIVE LOGITS
    åIJĦæł¡
    0.09
    约èĢĮåIJĮ
    0.09
    åIJĦ家
    0.09
    åIJĦèĩªçļĦ
    0.08
    åIJĦèĩª
    0.08
     shared
    0.07
     consensus
    0.07
     correctness
    0.07
     Issue
    0.07
    Issue
    0.07
    Activations Density 0.013%

    No Known Activations