© 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. 23669
    Prev
    Next
    INDEX
    Explanations

    geographical locations and borders

    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¸įçķı
    -0.07
     global
    -0.07
     randomly
    -0.07
    aky
    -0.06
    åħ¨çIJĥ
    -0.06
    random
    -0.06
    éķ¿ç©º
    -0.06
    anen
    -0.06
    global
    -0.06
    FromString
    -0.06
    POSITIVE LOGITS
    æ¯ĹéĤ»
    0.13
     neighboring
    0.13
     adjacent
    0.13
    éĤ»è¿ij
    0.13
    缸éĤ»
    0.12
     border
    0.11
    Adjacent
    0.11
     adjoining
    0.11
    交çķĮå¤Ħ
    0.11
    æݥ壤
    0.11
    Activations Density 0.399%

    No Known Activations