© 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. 10914
    Prev
    Next
    INDEX
    Explanations

    category names or math notation

    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
    æīĺ
    -0.08
    etos
    -0.07
    enius
    -0.06
    uros
    -0.06
    Å¡Å¥
    -0.06
    ibu
    -0.06
    {:
    -0.06
    andelier
    -0.06
    æij©
    -0.06
     ÙħÙĨÙĩ
    -0.06
    POSITIVE LOGITS
    icano
    0.07
    èķ´åIJ«
    0.07
    éo
    0.07
    esame
    0.07
    ovsky
    0.07
    ardown
    0.07
    á»ħn
    0.07
    _indexes
    0.07
    积æŀģåĪĨåŃIJ
    0.07
    .ta
    0.07
    Activations Density 0.007%

    No Known Activations