© 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. 31659
    Prev
    Next
    INDEX
    Explanations

    special characters and non-English words

    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
    éĺ³æĺ¥
    -0.08
    èıĬèĬ±
    -0.08
    chant
    -0.08
    arin
    -0.07
    _san
    -0.07
    ajok
    -0.07
    ç¬ijäºĨ
    -0.07
    заÑĢ
    -0.07
    /select
    -0.07
    frika
    -0.07
    POSITIVE LOGITS
     Paci
    0.08
    cot
    0.06
     recurs
    0.06
    çļ®è´¨
    0.06
    åŃĺè´§
    0.06
    åħ¬å¼ı
    0.06
     formula
    0.06
    sev
    0.06
    å¤ĩ
    0.06
     epid
    0.06
    Activations Density 0.006%

    No Known Activations