© 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. 30169
    Prev
    Next
    INDEX
    Explanations

    equipment

    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
    è¿Ļ款车
    -0.08
    شتÙĩ
    -0.08
    endale
    -0.08
    :hidden
    -0.08
    åĪĩåı£
    -0.08
    enfant
    -0.07
    orget
    -0.07
    _ENTITY
    -0.07
    ihar
    -0.07
     tráfico
    -0.07
    POSITIVE LOGITS
    设å¤ĩçļĦ
    0.15
     equipment
    0.15
    设å¤ĩ
    0.14
    è£ħå¤ĩ
    0.13
    -equipped
    0.13
    è¨ŃåĤĻ
    0.12
    设å¤ĩåĴĮ
    0.12
     обоÑĢÑĥдованиÑı
    0.11
    equipment
    0.11
    ç²¾èī¯
    0.11
    Activations Density 0.456%

    No Known Activations