© 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. 57508
    Prev
    Next
    INDEX
    Explanations

    algebraic expressions and variables

    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
    æĪIJç«ł
    -0.08
    áĥ®áĥĿ
    -0.08
    wiss
    -0.08
    gaz
    -0.08
    èĩĺ
    -0.08
    bauer
    -0.08
    .pm
    -0.08
    -default
    -0.08
    ecke
    -0.08
    hum
    -0.07
    POSITIVE LOGITS
    æĩ
    0.07
    YYY
    0.07
    å®ŀåĬĽçļĦ
    0.06
    ä¸īå±Ĥ
    0.06
    ä½ĵ积
    0.06
    SA
    0.06
    åı£æľį液
    0.06
    åĬĽçļĦ
    0.06
    ç«ĭæĸ¹ç±³
    0.06
    isa
    0.06
    Activations Density 0.006%

    No Known Activations