© 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. 43588
    Prev
    Next
    INDEX
    Explanations

    just before clauses or adjectives

    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
    aler
    -0.07
    ç»Īäºİ
    -0.07
    ä½Ĩä¹Ł
    -0.07
    ä¸Ģ头
    -0.06
     جد
    -0.06
    afen
    -0.06
     tam
    -0.06
    èİĺ
    -0.06
    å·¦åı³çļĦ
    -0.06
    å®ģæĦ¿
    -0.06
    POSITIVE LOGITS
     saja
    0.10
    WAIT
    0.08
    ãģ¡ãģ«
    0.08
    bery
    0.08
    éĤ£ä¹Īç®Ģåįķ
    0.08
     کاÙģÛĮ
    0.08
    èĢĮå·²
    0.08
     wenige
    0.07
    ardino
    0.07
    othe
    0.07
    Activations Density 0.236%

    No Known Activations