© 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. 4138
    Prev
    Next
    INDEX
    Explanations

    Arabic place names and locations

    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
    “
    -0.07
     sl
    -0.06
    Äħtek
    -0.06
    à¦¿à¦ľ
    -0.06
    ahuan
    -0.06
    éĩį
    -0.06
     Vietnamese
    -0.06
    çĸı
    -0.05
     vere
    -0.05
    ãģĵãģĨ
    -0.05
    POSITIVE LOGITS
    lesen
    0.08
     specially
    0.08
    0.08
    ökk
    0.08
    ebles
    0.08
    滨河
    0.07
    æĶ¯æĮģåĴĮ
    0.07
    azzi
    0.07
    azioni
    0.07
    èĬĿåĬł
    0.07
    Activations Density 0.043%

    No Known Activations