© 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. 64232
    Prev
    Next
    INDEX
    Explanations

    position .com approach exchange

    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
    ovar
    -0.08
    sic
    -0.07
    su
    -0.07
     lit
    -0.07
     <<-
    -0.07
    ikit
    -0.06
    imon
    -0.06
    满满çļĦ
    -0.06
    lit
    -0.06
    smith
    -0.06
    POSITIVE LOGITS
    å¯¹æľ¬æ¬¡
    0.08
    _typeof
    0.07
    ãģ¯ãĤĤãģ¡ãĤįãĤĵ
    0.07
    ibur
    0.07
    _compat
    0.07
    reement
    0.07
    inspace
    0.07
     kamp
    0.07
     racc
    0.07
    gle
    0.07
    Activations Density 0.003%

    No Known Activations