© 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. 50259
    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
     dam
    -0.08
    olars
    -0.07
    бÑĥÑĤ
    -0.07
    èĽ¾
    -0.07
    errick
    -0.07
    /inc
    -0.07
    åŀĴ
    -0.07
    erial
    -0.06
    oma
    -0.06
    çļĦè¾¹ç¼ĺ
    -0.06
    POSITIVE LOGITS
    hdl
    0.08
    çļĦæŶåĢĻä¸Ģå®ļè¦ģ
    0.07
    ÐĺС
    0.07
    agus
    0.06
    upro
    0.06
    _hook
    0.06
    tori
    0.06
    å½¢æĪIJäºĨä¸Ģ个
    0.06
     simply
    0.06
    åIJĪ家
    0.06
    Activations Density 0.000%

    No Known Activations