© 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. 56012
    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
    Ö¼
    -0.11
    onel
    -0.11
    lenme
    -0.10
    ÅĽcie
    -0.10
    enticate
    -0.10
    urgia
    -0.10
    gende
    -0.10
    꽤
    -0.09
    ÙĥÙĨت
    -0.09
    СТÐIJ
    -0.09
    POSITIVE LOGITS
    ç²Ĺæļ´
    0.09
    -
    0.08
    åľ°è¯´
    0.08
    ingly
    0.07
    s
    0.07
    (
    0.07
    2
    0.07
    ed
    0.07
    3
    0.07
    rev
    0.07
    Activations Density 0.000%

    No Known Activations