© 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. 22372
    Prev
    Next
    INDEX
    Explanations

    millions of rows/records

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ç¨Ģå¥ĩ
    -0.07
    ropp
    -0.07
    maz
    -0.07
    arov
    -0.07
    æł©æł©
    -0.06
     fusion
    -0.06
    onica
    -0.06
    fusion
    -0.06
    è¡°èĢģ
    -0.06
    éĶĢ
    -0.06
    POSITIVE LOGITS
    åįķè¾¹
    0.07
    irchen
    0.07
    个çĤ¹
    0.07
    åįķ缸
    0.07
    ição
    0.07
    åıĮéĿ¢
    0.07
    loid
    0.07
    .getStyle
    0.07
    ipun
    0.07
    SSERT
    0.06
    Activations Density 0.028%

    No Known Activations