© 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. 33938
    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
    为转载
    -0.07
    delen
    -0.07
    beg
    -0.06
    çĨŁç»ĥæĵįä½ľ
    -0.06
    è¿ŀè¿ŀ
    -0.06
    imetype
    -0.06
    ecam
    -0.06
    çĶľçĶľçļĦ
    -0.06
    кок
    -0.06
    Fetcher
    -0.06
    POSITIVE LOGITS
    éĥİ
    0.08
    ainen
    0.08
    ELD
    0.07
    mund
    0.07
    enus
    0.07
    豫
    0.07
    ÙĪدÙĬ
    0.07
    åĮĸ身
    0.07
    rawer
    0.07
     itemprop
    0.07
    Activations Density 0.000%

    No Known Activations