© 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. 49909
    Prev
    Next
    INDEX
    Explanations

    another or other followed by a noun

    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
    baru
    -0.08
    reste
    -0.08
    iap
    -0.07
    以赴
    -0.07
    oline
    -0.07
    ä»ħä»£è¡¨ä½ľèĢħæľ¬äºº
    -0.07
     ×Ķ×ĸ×Ķ
    -0.07
     unanim
    -0.07
    apu
    -0.07
    å¿ħ究
    -0.07
    POSITIVE LOGITS
    Ĭ
    0.08
    åı¯æĢľ
    0.07
     peer
    0.07
    åIJĮç±»
    0.07
    åħĦå¼Ł
    0.07
    world
    0.07
    æ¯Ķèĩªå·±
    0.07
    åĴĮèĩªå·±
    0.07
    éŵ
    0.06
     prot
    0.06
    Activations Density 0.181%

    No Known Activations