© 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. 39245
    Prev
    Next
    INDEX
    Explanations

    polygon points

    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
     Tun
    -0.08
     tuning
    -0.08
    lee
    -0.07
    _TUN
    -0.07
     disin
    -0.07
     tuned
    -0.07
     QName
    -0.07
     jack
    -0.07
    æ¡¥éķĩ
    -0.07
    Äı
    -0.07
    POSITIVE LOGITS
     polygon
    0.08
    éros
    0.08
     Revel
    0.08
     Interior
    0.07
    crimin
    0.07
    _polygon
    0.07
     glVertex
    0.07
    polygon
    0.07
    .concat
    0.07
    pts
    0.07
    Activations Density 0.004%

    No Known Activations