© 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. 64244
    Prev
    Next
    INDEX
    Explanations

    state changes or completion

    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
    èĭ¹
    -0.07
    isal
    -0.07
    ategoria
    -0.07
    LastError
    -0.07
    (Op
    -0.07
    _ARGS
    -0.07
    _TODO
    -0.06
    òi
    -0.06
    æŶæŶ
    -0.06
    èĢĺ
    -0.06
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.08
    rafo
    0.07
    ä¸įè¾¾
    0.07
    æ¸Īãģ¿
    0.07
    ä¸Ńåĩºçİ°
    0.07
    osse
    0.07
    ÙĨاد
    0.06
    orting
    0.06
    rey
    0.06
    orio
    0.06
    Activations Density 0.045%

    No Known Activations