© 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. 22670
    Prev
    Next
    INDEX
    Explanations

    links or lists with "+"

    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
    IZAR
    -0.07
    izar
    -0.07
    uus
    -0.07
    ku
    -0.07
    dade
    -0.07
    åĪ°ä¸ĭ
    -0.07
    _DEN
    -0.06
    åħ¼
    -0.06
    åij¦
    -0.06
    kip
    -0.06
    POSITIVE LOGITS
    æĸĩåįİ
    0.08
    æĺ¾
    0.07
    iment
    0.07
     acaso
    0.07
    éĢĤå½ĵ
    0.07
     Ponte
    0.07
     whatever
    0.07
    imento
    0.07
    å¤įåĪ¶æĪĸ
    0.07
     somehow
    0.07
    Activations Density 0.007%

    No Known Activations