© 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. 55514
    Prev
    Next
    INDEX
    Explanations

    city, mayor, streets, municipal

    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
     Rockies
    -0.09
     ranch
    -0.09
     Ranch
    -0.09
     Appalach
    -0.09
    çī§åľº
    -0.09
     Plains
    -0.09
    广袤
    -0.08
     Appalachian
    -0.08
     Arkansas
    -0.08
    åĨľåŀ¦
    -0.08
    POSITIVE LOGITS
    çŃīåŁİå¸Ĥ
    0.16
     urban
    0.16
     city
    0.16
    åŁİå¸Ĥ
    0.15
    è¡Ĺéģĵ
    0.15
     street
    0.15
    å¸Ĥ容
    0.15
    çļĦåŁİå¸Ĥ
    0.15
     streets
    0.14
    è¡Ĺ
    0.14
    Activations Density 0.700%

    No Known Activations