© 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. 13347
    Prev
    Next
    INDEX
    Explanations

    in favor of

    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
    åīįåIJİ
    -0.07
    羸
    -0.07
    ä¸Ń西åĮ»
    -0.07
    çĶ·å¥³
    -0.07
     arch
    -0.06
    éco
    -0.06
    çݯ
    -0.06
    å¢ŀåĩı
    -0.06
    é«ĺä½İ
    -0.06
    åıĪå¦Ĥ
    -0.06
    POSITIVE LOGITS
    åIJİèĢħ
    0.11
    åīįèĢħ
    0.10
    ãģ©ãģ¡ãĤī
    0.09
     latter
    0.09
    nty
    0.09
     именно
    0.09
     Ñģаме
    0.08
    åIJİæĦŁ
    0.08
    less
    0.08
     letz
    0.07
    Activations Density 0.242%

    No Known Activations