© 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. 38737
    Prev
    Next
    INDEX
    Explanations

    Arctic and Antarctic regions

    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©·
    -0.07
    inha
    -0.07
    æ¸ł
    -0.07
    åĸľåºĨ
    -0.07
    å¦Ĥ鼨
    -0.07
    oci
    -0.06
    æī¹æ¬¡
    -0.06
     Ä°zmir
    -0.06
    åĽŃè·¯
    -0.06
    jay
    -0.06
    POSITIVE LOGITS
    åĮĹæŀģ
    0.12
     Arctic
    0.11
     Greenland
    0.10
    æŀģåľ°
    0.10
     Antarctic
    0.09
     sled
    0.09
    åįĹæŀģ
    0.09
     Alaska
    0.09
    鼶ä¸ĭ
    0.08
    åĨ°éĽª
    0.08
    Activations Density 0.068%

    No Known Activations