© 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. 22008
    Prev
    Next
    INDEX
    Explanations

    data structure representations

    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
    uret
    -0.07
     committed
    -0.06
    others
    -0.06
     бла
    -0.06
     stil
    -0.06
     nou
    -0.06
     abide
    -0.05
     officially
    -0.05
    çª
    -0.05
    èķĥ
    -0.05
    POSITIVE LOGITS
    azier
    0.09
     č↵ č↵
    0.08
    iente
    0.08
    hoto
    0.08
    é«ĺæķĪ
    0.08
    IBUT
    0.08
    hini
    0.08
    é«ĺæķĪçļĦ
    0.08
    åªĽåªĽ
    0.08
    ientes
    0.08
    Activations Density 0.004%

    No Known Activations