© 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. 10463
    Prev
    Next
    INDEX
    Explanations

    migration and displacement

    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¯ŀè¾°
    -0.08
    贯穿
    -0.07
    lut
    -0.07
    éĢļè¿ĩè¿ĻäºĽ
    -0.07
    贯穿äºİ
    -0.07
    lh
    -0.07
    åIJĿ
    -0.07
    æĮīæŶå®ĮæĪIJ
    -0.06
    ä»ĺ
    -0.06
    unic
    -0.06
    POSITIVE LOGITS
    è¿ģ移
    0.13
     migration
    0.12
     relocated
    0.11
    å®ļå±ħ
    0.11
     relocation
    0.11
    转移åĪ°
    0.11
    migration
    0.11
     resett
    0.10
    转移
    0.10
     fleeing
    0.10
    Activations Density 0.283%

    No Known Activations