© 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. 14978
    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
    ¹Ħ
    -0.09
    iaan
    -0.08
    ezer
    -0.08
    beau
    -0.08
    ich
    -0.08
     Bakal
    -0.08
    illac
    -0.08
     dep
    -0.08
    heimer
    -0.07
    ĥģ
    -0.07
    POSITIVE LOGITS
     Hom
    0.06
    ote
    0.06
    оÑĤи
    0.06
    jective
    0.06
    导管
    0.06
    .execute
    0.06
    ulo
    0.06
    íĸīìĿĦ
    0.06
     Fr
    0.06
     Pad
    0.06
    Activations Density 0.000%

    No Known Activations