© 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. 4399
    Prev
    Next
    INDEX
    Explanations

    dimensions and rank

    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
    管çIJĨå§Ķåijĺä¼ļ
    -0.07
    èĭ¦ç»ĥ
    -0.07
    DB
    -0.07
    asma
    -0.06
    ZEN
    -0.06
    ãĥ¡ãĥª
    -0.06
    骼
    -0.06
    åĵī
    -0.06
    æĮīåħ¶
    -0.06
    åľ¨æīĢ
    -0.06
    POSITIVE LOGITS
    reau
    0.08
    ç»´å¥ĩ
    0.07
    arger
    0.07
    fel
    0.07
    ffi
    0.07
    ÑĢил
    0.07
    .setOn
    0.07
    ifers
    0.07
    ä»»ä½ķä¿Ŀè¯ģ
    0.07
     Nielsen
    0.06
    Activations Density 0.063%

    No Known Activations