© 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. 63004
    Prev
    Next
    INDEX
    Explanations

    divided by

    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
    sWith
    -0.07
    èıľ
    -0.06
    ouve
    -0.06
    ing
    -0.06
    ä»ķ
    -0.06
    ale
    -0.06
    人以ä¸Ĭ
    -0.06
    ÑĢÑİ
    -0.06
    ç³»åĪĹ
    -0.06
     Jo
    -0.06
    POSITIVE LOGITS
    æīĢå±ŀåĪĨç±»
    0.09
    ående
    0.09
    blia
    0.08
    ÙĪاج
    0.08
     éppen
    0.08
    ritten
    0.08
    liers
    0.07
    ÏĦια
    0.07
    ADED
    0.07
    idado
    0.07
    Activations Density 0.083%

    No Known Activations