© 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. 23213
    Prev
    Next
    INDEX
    Explanations

    try to learn

    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
    浪
    -0.07
     Coun
    -0.07
    çĥĪ
    -0.06
    UM
    -0.06
     fre
    -0.06
     (...)
    -0.06
    _EXTERN
    -0.06
    -flat
    -0.06
    um
    -0.06
    _provider
    -0.06
    POSITIVE LOGITS
    è¯Ħä»·ä½ĵç³»
    0.08
    enne
    0.08
    ynos
    0.08
    èĥ½èĢIJ
    0.08
    é¦ĸé¢Ĩ
    0.07
    artos
    0.07
    enha
    0.07
    _$
    0.07
    oples
    0.07
    enk
    0.07
    Activations Density 0.001%

    No Known Activations