© 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. 57021
    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
    opher
    -0.07
    ihi
    -0.07
    è¶Ĭèµ°
    -0.07
    lesa
    -0.07
    enko
    -0.07
    ovo
    -0.07
    kich
    -0.07
    esco
    -0.07
    etton
    -0.07
    Ĥ¹
    -0.07
    POSITIVE LOGITS
    çĦ¶
    0.08
    ound
    0.07
    teo
    0.07
    纶
    0.07
    让åIJĮåѦ们
    0.07
    .io
    0.07
    订ç«ĭ
    0.07
    太åŃIJ
    0.07
    åĴĮ人æ°ij
    0.06
    OUND
    0.06
    Activations Density 0.000%

    No Known Activations