© 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. 45945
    Prev
    Next
    INDEX
    Explanations

    wheel and related parts

    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
    ï¾ŀ
    -0.09
    mals
    -0.08
    ãĥ¬ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.07
    laÅŁ
    -0.07
    dır
    -0.07
    ercial
    -0.07
    راع
    -0.07
    estic
    -0.07
    OrUpdate
    -0.07
    ourn
    -0.07
    POSITIVE LOGITS
    edReader
    0.08
    isode
    0.08
    wright
    0.08
    ä¸Ģ转
    0.08
    jest
    0.08
    istico
    0.07
    chair
    0.07
    worm
    0.07
    belt
    0.07
    еÑĤÑĮ
    0.07
    Activations Density 0.024%

    No Known Activations