© 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. 23593
    Prev
    Next
    INDEX
    Explanations

    service or sprint

    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
    áºŃm
    -0.06
    lius
    -0.06
    els
    -0.06
    ienne
    -0.06
    ä¸ĢèĬĤ
    -0.06
    æĢ»ç®Ĺ
    -0.06
    æĮĩå¼ķ
    -0.06
    ild
    -0.06
    alia
    -0.05
    lay
    -0.05
    POSITIVE LOGITS
    æĿı
    0.08
    书åıĭ
    0.08
    _EXTENSIONS
    0.08
    ÙĦÙĥ
    0.08
    å³Ļ
    0.07
    EGI
    0.07
    rollo
    0.07
    .$.
    0.07
    ondi
    0.07
    åīįèĢħ
    0.07
    Activations Density 0.115%

    No Known Activations