© 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. 63279
    Prev
    Next
    INDEX
    Explanations

    legal document outcomes

    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
    äºĨçĦ¶
    -0.08
    ä¿Ŀè¯ģåħ¶
    -0.08
    ä¿Ŀéļľæݪæĸ½
    -0.07
    yder
    -0.07
     inherently
    -0.07
    ä¿Ŀéļľ
    -0.07
    inder
    -0.07
    ç¼Ģ
    -0.07
     lain
    -0.07
    und
    -0.07
    POSITIVE LOGITS
    alang
    0.09
     conclu
    0.08
    强æľīåĬĽçļĦ
    0.08
    acci
    0.08
     conclude
    0.08
    pars
    0.08
     Pars
    0.07
    æľīåĬĽçļĦ
    0.07
     pars
    0.07
    å¼·åĬĽ
    0.07
    Activations Density 0.002%

    No Known Activations