© 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. 19118
    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
    oubl
    -0.07
    æļ§
    -0.07
    è¾¾åħĭ
    -0.07
    etil
    -0.07
    OnError
    -0.07
    opor
    -0.07
    ummer
    -0.06
    uide
    -0.06
     favour
    -0.06
    worth
    -0.06
    POSITIVE LOGITS
    ubr
    0.08
    ׾×ĺ
    0.07
    UGIN
    0.07
    μά
    0.07
    usal
    0.07
    /WebAPI
    0.07
     keras
    0.07
    ieniem
    0.06
    panion
    0.06
    -save
    0.06
    Activations Density 0.000%

    No Known Activations