© 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. 2678
    Prev
    Next
    INDEX
    Explanations

    city names

    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
    imon
    -0.09
    ļĮ
    -0.07
    -img
    -0.07
    ACO
    -0.07
     Patron
    -0.07
     kese
    -0.07
    æĹłè·¯
    -0.06
    åīįåĪĹ
    -0.06
     indirectly
    -0.06
    éĺ¿åį¡
    -0.06
    POSITIVE LOGITS
    -wide
    0.07
    å¹´ä»ħ
    0.07
    erah
    0.07
     ambient
    0.07
    ovi
    0.06
    ä¸ĵèģĮ
    0.06
    çļĦåħ³æ³¨
    0.06
     Compart
    0.06
    sic
    0.06
    andbox
    0.06
    Activations Density 0.398%

    No Known Activations