© 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. 19248
    Prev
    Next
    INDEX
    Explanations

    second order derivative

    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
    гал
    -0.09
    USTA
    -0.08
    iasco
    -0.08
    prost
    -0.08
    天éķ¿
    -0.08
    ilas
    -0.08
    å½ĵ头
    -0.08
    ÏĦÏİ
    -0.08
    yeti
    -0.08
    getti
    -0.08
    POSITIVE LOGITS
    -order
    0.09
    -level
    0.08
     derivative
    0.08
     level
    0.07
    -degree
    0.07
    âĢIJ
    0.06
     derivatives
    0.06
    导
    0.06
     einsch
    0.06
    -dimensional
    0.06
    Activations Density 0.014%

    No Known Activations