© 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. 34561
    Prev
    Next
    INDEX
    Explanations

    wind speed or damage

    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
    Ù°
    -0.09
    hips
    -0.08
    ramid
    -0.08
    à¤ķरण
    -0.07
    çIJ²
    -0.07
    kasse
    -0.07
     kÃŃv
    -0.07
    à¹Ģมà¹ĩà¸Ķ
    -0.07
    à¥įड
    -0.07
    eger
    -0.06
    POSITIVE LOGITS
     веÑĤÑĢа
    0.11
    æĭĤ
    0.10
    wind
    0.09
    lett
    0.08
    éĺµéĺµ
    0.08
    é£İåĬĽ
    0.08
     gust
    0.08
    iness
    0.08
    ken
    0.08
    åij¼åij¼
    0.08
    Activations Density 0.026%

    No Known Activations