© 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. 43480
    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
    anko
    -0.08
    请ä¸ĭè½½
    -0.08
    által
    -0.08
    isant
    -0.08
    utori
    -0.08
    为建设
    -0.07
    anders
    -0.07
    /Application
    -0.07
    ars
    -0.07
    å°Ħæīĭ
    -0.07
    POSITIVE LOGITS
    itud
    0.07
     vs
    0.07
     decl
    0.07
    缸è¾ħ缸æĪIJ
    0.06
    chten
    0.06
    aum
    0.06
    yman
    0.06
    itat
    0.06
    itational
    0.06
    ily
    0.05
    Activations Density 0.000%

    No Known Activations