© 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. 30266
    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
    åľ¨è¿Ļæł·çļĦ
    -0.08
    æľī个
    -0.07
    ronic
    -0.07
     scratch
    -0.07
    对äºİè¿ĻäºĽ
    -0.06
    uis
    -0.06
    éĻĦè¿ijæľī
    -0.06
     crunch
    -0.06
    ercul
    -0.06
    uas
    -0.06
    POSITIVE LOGITS
    ncmp
    0.09
    imy
    0.08
    jal
    0.07
    inste
    0.07
    绯
    0.07
    /utility
    0.07
    igna
    0.06
    hay
    0.06
    fw
    0.06
    juven
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.