© 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. 48516
    Prev
    Next
    INDEX
    Explanations

    African countries and cities

    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
    人åijĺè§Ħ模
    -0.07
    otka
    -0.07
     nonprofit
    -0.07
    æĦıæ°Ķ
    -0.07
    ãĥ¬ãĥĥ
    -0.07
     nonprofits
    -0.07
    irsch
    -0.07
    çĪ±æ°ij
    -0.07
    ihad
    -0.06
     Schla
    -0.06
    POSITIVE LOGITS
     Africans
    0.10
     Ejem
    0.09
    éĿŀæ´²
    0.09
     Cameroon
    0.08
     Ghana
    0.08
     Nairobi
    0.08
     Africa
    0.08
     Nigerian
    0.08
     Uganda
    0.08
     Nigeria
    0.08
    Activations Density 0.837%

    No Known Activations