© 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. 17049
    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
    rush
    -0.08
    AtPath
    -0.08
    andid
    -0.08
    داء
    -0.08
    ništ
    -0.08
    ******/
    -0.08
    idia
    -0.08
    istory
    -0.07
    zyn
    -0.07
    zio
    -0.07
    POSITIVE LOGITS
    ìĦĿìĿĦ
    0.07
    ìĦĿ
    0.07
    her
    0.07
    æīİæīİå®ŀ
    0.06
    lo
    0.06
    lar
    0.06
    without
    0.06
    log
    0.06
    \n
    0.06
    opf
    0.06
    Activations Density 0.000%

    No Known Activations