© 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. 28034
    Prev
    Next
    INDEX
    Explanations

    members of government or boards

    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
    å·¥åķĨ注åĨĮåı·
    -0.09
    agni
    -0.08
    æľªå®Į
    -0.07
    æ¯į女
    -0.07
    çľģå§Ķ书记
    -0.07
    æĥ³å¾ĹåĪ°
    -0.07
    天çĽĸ
    -0.07
    çŃĭ
    -0.07
    å¸Ŀçİĭ
    -0.07
    缸åħ³éĥ¨éŨæī¹åĩĨ
    -0.07
    POSITIVE LOGITS
     appointments
    0.10
     slots
    0.09
    ä»»æľŁ
    0.09
    åIJįé¢Ŀ
    0.09
     appointed
    0.09
     Slots
    0.08
     selections
    0.08
    è½®æį¢
    0.08
     appoint
    0.08
     seats
    0.08
    Activations Density 0.330%

    No Known Activations