© 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. 46644
    Prev
    Next
    INDEX
    Explanations

    startup and venture capital

    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
    奴
    -0.08
    atha
    -0.07
     supp
    -0.07
    å¨ģ严
    -0.07
     discharge
    -0.07
    yum
    -0.06
    dealer
    -0.06
    Scheduled
    -0.06
     motorists
    -0.06
    çĶŁäº§åİĤ家
    -0.06
    POSITIVE LOGITS
     startup
    0.12
     startups
    0.12
    åĪĽä¸ļ
    0.12
     incub
    0.12
     founders
    0.12
    åĪĽä¸ļèĢħ
    0.11
     Startup
    0.11
    åѵåĮĸ
    0.11
    åĪĽå§ĭ
    0.11
    startup
    0.10
    Activations Density 0.347%

    No Known Activations