© 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. 57186
    Prev
    Next
    INDEX
    Explanations

    longitude and latitude

    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
     semestre
    -0.08
    uster
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    phas
    -0.07
    orque
    -0.07
    太ä»ĵ
    -0.07
    声åĬ¿
    -0.07
    çĩİ
    -0.07
    è¿Ļ个éĺ¶æ®µ
    -0.07
    atement
    -0.07
    POSITIVE LOGITS
     longitude
    0.11
     latitude
    0.11
    åĮĹ纬
    0.10
    ç»ı纬
    0.10
     north
    0.10
     west
    0.09
     coordinates
    0.09
     гÑĢадÑĥÑģ
    0.09
     geographic
    0.09
     geo
    0.08
    Activations Density 0.048%

    No Known Activations