© 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. 15058
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical expressions

    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
    ç«ĻåĨħæIJľç´¢
    -0.09
    iers
    -0.08
    astos
    -0.08
    ITHER
    -0.08
    yk
    -0.08
    pcf
    -0.08
    \:
    -0.07
    orsa
    -0.07
    书åIJ§
    -0.07
    yki
    -0.07
    POSITIVE LOGITS
    æŀģéĻIJ
    0.08
    æĹłéĻIJ
    0.07
    éļıçĿĢ
    0.07
    alak
    0.07
     limit
    0.07
     asympt
    0.07
     constant
    0.07
     lim
    0.06
    æ°¸ä¹ħ
    0.06
    OMO
    0.06
    Activations Density 0.002%

    No Known Activations