© 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. 18863
    Prev
    Next
    INDEX
    Explanations

    letters and numbers in parentheses

    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
    -ng
    -0.08
    ÏĨÏħ
    -0.07
     اÙĦصÙģ
    -0.07
     réparation
    -0.07
    éĩįçļĦ
    -0.07
    ä¸įè¾ľè´Ł
    -0.07
    urgo
    -0.07
    vice
    -0.06
    incipe
    -0.06
     اÙĦÙĤص
    -0.06
    POSITIVE LOGITS
    ãĢģ
    0.07
    _DEFINE
    0.06
     &
    0.06
    寰
    0.06
    åįĥæĸ¹
    0.06
    _subtype
    0.06
    jä
    0.06
    é¢ĺå¹²
    0.06
     Lawson
    0.06
    éĵ¶æ²³
    0.06
    Activations Density 0.002%

    No Known Activations