© 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. 23067
    Prev
    Next
    INDEX
    Explanations

    building relationships and trust

    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
    社ä¼ļåıijå±ķ
    -0.08
    StateChanged
    -0.08
    assel
    -0.08
    TextChanged
    -0.07
     antics
    -0.07
    atico
    -0.07
    大èĩªçĦ¶çļĦ
    -0.07
    aminh
    -0.07
    urrent
    -0.07
    äºĨ大éĩıçļĦ
    -0.07
    POSITIVE LOGITS
     lasting
    0.10
    èī¯å¥½çļĦ
    0.10
     trust
    0.09
     vững
    0.09
     understanding
    0.09
     confidence
    0.09
    çī¢åĽº
    0.09
     strong
    0.09
    建ç«ĭèµ·
    0.09
     rapport
    0.09
    Activations Density 0.126%

    No Known Activations