© 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. 56927
    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
    éĩijæĸ¯
    -0.08
    ÙģÙĬر
    -0.07
    entr
    -0.07
    åħĭ森
    -0.07
    "./
    -0.07
    aing
    -0.07
    [:,:,
    -0.07
    åĿĬ
    -0.07
    åIJIJåĩº
    -0.07
    endorf
    -0.07
    POSITIVE LOGITS
    æĺķ
    0.07
    åĵĴ
    0.06
    cest
    0.06
    orsa
    0.06
    èĥ¡æ¡ĥ
    0.06
    ollower
    0.06
     nip
    0.06
    è¯Ĺæĥħ
    0.06
    eb
    0.06
    riere
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.