© 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. 20602
    Prev
    Next
    INDEX
    Explanations

    circular around

    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
    ä¸Ģå¼łå¼ł
    -0.08
    uct
    -0.08
    ombo
    -0.08
    ä¸įä¹±
    -0.08
    Ïĩο
    -0.08
    ianza
    -0.08
    åĨį说
    -0.08
    nger
    -0.08
    ->__
    -0.08
    Leist
    -0.07
    POSITIVE LOGITS
    å¦ĤåĽ¾æīĢ示
    0.07
    å°Ĩä¸Ģ个
    0.07
    bek
    0.07
    çĶ²
    0.06
    iley
    0.06
    温度为
    0.06
    A
    0.06
    çİ°å°Ĩ
    0.06
     \(
    0.06
    COVID
    0.06
    Activations Density 0.074%

    No Known Activations