© 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. 64102
    Prev
    Next
    INDEX
    Explanations

    Comparison operators with null/none

    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
    ÄįiÄĩ
    -0.07
    ../../../
    -0.07
    e
    -0.07
    åĪ¶éĢł
    -0.07
    ic
    -0.06
    éħĿ
    -0.06
    iring
    -0.06
    æĺ¯å¥½
    -0.06
    è½¬çľ¼
    -0.06
    Ñĩик
    -0.06
    POSITIVE LOGITS
    pired
    0.08
    urgy
    0.08
    รà¸ģ
    0.08
    unned
    0.07
    ness
    0.07
    nul
    0.07
    urang
    0.07
    à¹Īาà¸ĩ
    0.07
    incr
    0.07
    nél
    0.07
    Activations Density 0.019%

    No Known Activations