© 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. 31768
    Prev
    Next
    INDEX
    Explanations

    H2O2 or O2

    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
    Ùĩ
    -0.09
    er
    -0.09
    u
    -0.08
    en
    -0.08
    al
    -0.08
    ive
    -0.07
    ب
    -0.07
    ìĸ´
    -0.07
    /or
    -0.07
    s
    -0.07
    POSITIVE LOGITS
    ceans
    0.10
    ehme
    0.10
    俱ä¹IJéĥ¨
    0.09
    lymp
    0.09
    verture
    0.09
    portun
    0.09
    alkan
    0.09
    cean
    0.09
    ptions
    0.08
    innie
    0.08
    Activations Density 0.005%

    No Known Activations