© 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. 15745
    Prev
    Next
    INDEX
    Explanations

    place or location

    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
    åľ¨è¿Ļçīĩ
    -0.09
    æĸ¹éĺµ
    -0.07
    éĢļè¿ĩåľ¨
    -0.07
    åľ¨ä»ĸ们çļĦ
    -0.07
    åħ¨çº¿
    -0.07
    plat
    -0.07
     filib
    -0.07
    çĮĿ
    -0.07
    ikit
    -0.07
    velope
    -0.06
    POSITIVE LOGITS
     location
    0.10
    è¿ľç¦»
    0.09
    éĢĤå®ľ
    0.08
     locations
    0.08
     suitable
    0.08
    åŃĺæĶ¾
    0.08
     Location
    0.08
     idone
    0.08
     storage
    0.08
    ä¸ĵ人
    0.08
    Activations Density 0.075%

    No Known Activations