© 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. 28109
    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
    iii
    -0.07
    akit
    -0.07
    .EventType
    -0.07
    人说
    -0.07
     Tern
    -0.07
    _FUNC
    -0.07
    ÙĪÙĦØ©
    -0.07
    segn
    -0.07
     III
    -0.06
    å·¥ä½ľåľ°çĤ¹
    -0.06
    POSITIVE LOGITS
    adies
    0.07
    çļĦä¸Ģå¹´éĩĮ
    0.07
    inspir
    0.07
    åIJĦè¡Į
    0.07
    Toe
    0.07
    ameron
    0.07
    itled
    0.07
    ipas
    0.07
     SOCK
    0.07
    iris
    0.07
    Activations Density 0.000%

    No Known Activations