© 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. 50091
    Prev
    Next
    INDEX
    Explanations

    parsing numerical data, lists, and averages

    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
    coni
    -0.07
    å¤ĩ
    -0.07
    astre
    -0.06
     dangere
    -0.06
    iversal
    -0.06
    resse
    -0.06
     dangerous
    -0.06
     containment
    -0.06
    çī¹å®ļ
    -0.06
    妾
    -0.06
    POSITIVE LOGITS
     averages
    0.08
    åģıä½İ
    0.08
    å¹³åĿĩåĢ¼
    0.08
    اظ
    0.08
    ELLA
    0.07
     Aver
    0.07
     Petty
    0.07
    plets
    0.07
     variability
    0.07
    fet
    0.07
    Activations Density 0.039%

    No Known Activations