© 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. 42265
    Prev
    Next
    INDEX
    Explanations

    economics, psychology, bankruptcy, energy, development, grant

    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
    Whilst
    -0.08
     Whilst
    -0.08
     /
    -0.07
     Firstly
    -0.07
    semi
    -0.07
    尾巴
    -0.07
     harbour
    -0.06
     whilst
    -0.06
    容
    -0.06
     [
    -0.06
    POSITIVE LOGITS
    è¿ĶåĽŀ缮å½ķ
    0.09
     mithilfe
    0.08
    迸
    0.08
    tova
    0.08
    欣欣
    0.08
    <|box_end|>
    0.08
    è´Ŀåħĭ
    0.08
    izr
    0.08
    ırı
    0.08
     паÑĥ
    0.08
    Activations Density 0.020%

    No Known Activations