© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63841
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    epad
    -0.09
    enas
    -0.07
    obat
    -0.07
    jent
    -0.07
    vanced
    -0.07
    uppies
    -0.07
    atsby
    -0.07
    ìĤ¼
    -0.07
    renched
    -0.06
    è¡ĮåĬ¨ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    acher
    0.08
    禾
    0.07
    iete
    0.07
    itera
    0.07
    cep
    0.07
    ogh
    0.07
    çŃĶè°¢
    0.07
    _hostname
    0.06
    å±¥åİĨ
    0.06
    ophon
    0.06
    Activations Density 0.000%

    No Known Activations