© 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. 21723
    Prev
    Next
    INDEX
    Explanations

    charge-transfer transition

    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
    ä»
    -0.08
    ä½ij
    -0.07
    ayout
    -0.07
    ChangeEvent
    -0.07
     ge
    -0.07
    çĻ¾ç±³
    -0.06
    åįĥ人
    -0.06
    боÑİ
    -0.06
    oleon
    -0.06
    .serializer
    -0.06
    POSITIVE LOGITS
    åıįåIJij
    0.11
    åıįè¿ĩæĿ¥
    0.10
     reverse
    0.09
     наобоÑĢоÑĤ
    0.09
    Reverse
    0.09
    reverse
    0.08
     Reverse
    0.08
     sebaliknya
    0.08
    ondon
    0.08
     Conversely
    0.08
    Activations Density 0.002%

    No Known Activations