© 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. 31933
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, code, or medical terms

    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
    ¹
    -0.06
    ‘
    -0.06
     ‘
    -0.06
    /rec
    -0.06
    ewe
    -0.05
     epit
    -0.05
    çģ¯
    -0.05
     equally
    -0.05
    ↵
    -0.05
    POSITIVE LOGITS
    UDI
    0.09
    ç»Ŀåľ°
    0.08
    GBT
    0.08
    udian
    0.08
     adelant
    0.08
    UME
    0.08
    åįļæĸĩ
    0.08
    edt
    0.08
    stp
    0.08
    äºĨæĮĩ
    0.08
    Activations Density 0.004%

    No Known Activations