© 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. 3528
    Prev
    Next
    INDEX
    Explanations

    regions and continents

    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
    ä¸Ģç§į
    -0.07
    åľ¨å¸Ĥ
    -0.07
    åľ¨åİŁ
    -0.06
     Moraes
    -0.06
    好åŃ©åŃIJ
    -0.06
    åľ¨æŁIJ
    -0.06
    äºİä¸ĸ
    -0.06
    ä¹ĭä¸Ģ
    -0.06
    —one
    -0.06
    åľ¨åħ¨å¸Ĥ
    -0.06
    POSITIVE LOGITS
    éĥ¨åĪĨåľ°åĮº
    0.09
     southern
    0.09
     peninsula
    0.09
    çŃīåľ°åĮº
    0.09
    åįĹéĥ¨
    0.09
     northern
    0.09
    çĽĨåľ°
    0.09
    åĮĹ纬
    0.09
    以åįĹ
    0.08
     вклÑİÑĩаÑı
    0.08
    Activations Density 0.172%

    No Known Activations