© 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. 39679
    Prev
    Next
    INDEX
    Explanations

    JSON structure

    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
    ima
    -0.08
    tian
    -0.07
    heit
    -0.07
    /console
    -0.06
    éĵ¿
    -0.06
    ɵ
    -0.06
    æľį
    -0.06
    mán
    -0.06
    èĥĮä¸Ĭ
    -0.06
    åł±
    -0.06
    POSITIVE LOGITS
     Parten
    0.07
    æĸ°ç½ij
    0.07
    iable
    0.07
    indra
    0.07
    _Handler
    0.07
     spok
    0.07
    leh
    0.07
    Absent
    0.06
    ittest
    0.06
    奥çī¹
    0.06
    Activations Density 0.066%

    No Known Activations