© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17719
    Prev
    Next
    INDEX
    Explanations

    `<` and `>` comparison operators

    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
    HW
    -0.06
    à¸Ĺà¹īาย
    -0.06
    portes
    -0.06
    ataka
    -0.06
    ä¸įä¹ħçļĦ
    -0.06
    urd
    -0.06
    uro
    -0.06
    æ¸ħé£İ
    -0.06
    ën
    -0.06
    éĢģçļĦ
    -0.06
    POSITIVE LOGITS
    ä½¼
    0.08
    åºĦéķĩ
    0.08
    碧海
    0.08
    ä¸įæ¯Ķ
    0.08
    ä¸į缸
    0.08
    å½¼æѤ
    0.07
    ecas
    0.07
    ãĥŁãĥį
    0.07
    brtc
    0.07
    åºĻ
    0.07
    Activations Density 0.004%

    No Known Activations