© 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. 43034
    Prev
    Next
    INDEX
    Explanations

    intimate closeness

    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
    åĪĿ
    -0.08
     consistently
    -0.07
    resent
    -0.07
    åĭī
    -0.06
     systematically
    -0.06
    åIJĪä¹İ
    -0.06
    转转
    -0.06
     reliably
    -0.06
     steadily
    -0.06
    _bal
    -0.06
    POSITIVE LOGITS
    缴æİ¥æݥ触
    0.14
     intimate
    0.13
     intimacy
    0.12
    鼶è·Ŀ离
    0.12
    亲å¯Ĩ
    0.12
    å¯ĨåĪĩæݥ触
    0.12
    è¿ijè·Ŀ离
    0.12
     intime
    0.12
    æ·±åħ¥åĪ°
    0.12
    /close
    0.11
    Activations Density 0.260%

    No Known Activations