© 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. 46010
    Prev
    Next
    INDEX
    Explanations

    "So" followed by clauses or questions

    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
    èļ¤
    -0.08
    anz
    -0.08
    éĢĶ
    -0.08
    timb
    -0.08
    åİ»ä½ķ
    -0.07
    lox
    -0.07
    PageIndex
    -0.07
    antin
    -0.07
    antau
    -0.07
    bö
    -0.07
    POSITIVE LOGITS
    лаг
    0.07
    强è°ĥçļĦæĺ¯
    0.07
    çļĦæĺ¯ä¸Ģ个
    0.06
    enen
    0.06
    !
    0.06
    åħ³å¿ĥ
    0.06
    ä½łä¸įæĺ¯
    0.06
    wes
    0.06
    imak
    0.06
    &
    0.06
    Activations Density 0.006%

    No Known Activations