© 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. 50473
    Prev
    Next
    INDEX
    Explanations

    student or researcher context

    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
    æ³
    -0.08
    åģ
    -0.08
    åı¸
    -0.07
    ç«ĭ
    -0.07
     Leverkus
    -0.07
    pee
    -0.07
    ykk
    -0.07
    pees
    -0.07
    ORB
    -0.07
    fyl
    -0.07
    POSITIVE LOGITS
    erma
    0.07
    æĸ°çIJĨ念
    0.07
    è¯¥ä½ľèĢħ
    0.07
    åīį款
    0.07
    åŁİåįĹ
    0.07
    ниÑĨа
    0.07
    ahrung
    0.06
    æľīè°ģ
    0.06
    缸åħ³åįķä½į
    0.06
    neck
    0.06
    Activations Density 0.010%

    No Known Activations