© 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. 38510
    Prev
    Next
    INDEX
    Explanations

    floating point

    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
    e
    -0.07
    sf
    -0.06
    ek
    -0.06
    eke
    -0.06
     e
    -0.06
    s
    -0.06
    er
    -0.06
    erra
    -0.06
    -
    -0.05
    ize
    -0.05
    POSITIVE LOGITS
    bon
    0.09
    Ø´ÛĮÙĨ
    0.08
    ystack
    0.08
    onn
    0.08
    ×Ļ׳×ķ
    0.08
    >Title
    0.08
    PageIndex
    0.08
    ODEV
    0.08
    (Conv
    0.08
    CHANT
    0.08
    Activations Density 0.817%

    No Known Activations