© 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. 40275
    Prev
    Next
    INDEX
    Explanations

    latitude and hemisphere

    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
     postfix
    -0.07
    åIJĮäºĭ
    -0.07
    tps
    -0.07
    继
    -0.07
     predecessors
    -0.07
    ä¹ĭæķ°
    -0.07
     Moreira
    -0.06
    éļĶå¤ľ
    -0.06
    è¦ģä½ł
    -0.06
    eed
    -0.06
    POSITIVE LOGITS
     latitude
    0.11
    纬度
    0.10
    latitude
    0.09
    åĮĹ纬
    0.09
    ä»°
    0.09
     elevation
    0.08
     geographical
    0.08
    Latitude
    0.08
     north
    0.08
    纬
    0.08
    Activations Density 0.006%

    No Known Activations