© 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. 61045
    Prev
    Next
    INDEX
    Explanations

    latitude or longitude degrees

    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
    mus
    -0.08
    佩
    -0.07
    tron
    -0.07
    eki
    -0.07
    åĩºèĩª
    -0.07
    å¤ĸéĿ¢
    -0.06
    èĤ
    -0.06
    çĭŀ
    -0.06
    ngo
    -0.06
    å§Ĩæĸ¯
    -0.06
    POSITIVE LOGITS
    ObjectType
    0.07
    elig
    0.07
    .mix
    0.07
     Diag
    0.07
    åĮĹåIJij
    0.07
    æ¸ł
    0.07
    .ham
    0.07
     northwest
    0.07
    é»Ħæ¢ħ
    0.07
     Watches
    0.07
    Activations Density 0.076%

    No Known Activations