© 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. 12534
    Prev
    Next
    INDEX
    Explanations

    special characters in code

    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
    大åĸľ
    -0.06
    kee
    -0.06
    åĪ°æŶåĢĻ
    -0.06
    èĩ¼
    -0.06
    son
    -0.05
    ikul
    -0.05
    itar
    -0.05
     sized
    -0.05
    为å®ĺ
    -0.05
    åıĹç²¾
    -0.05
    POSITIVE LOGITS
    ')</
    0.08
    )new
    0.08
    glich
    0.08
    arov
    0.08
    lund
    0.08
    ulle
    0.07
     conmigo
    0.07
    _globals
    0.07
    æĹłéĻħ
    0.07
    dig
    0.07
    Activations Density 0.009%

    No Known Activations