© 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. 48623
    Prev
    Next
    INDEX
    Explanations

    injury or trauma

    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¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    Âł
    -0.07
    ÅĤka
    -0.06
     metric
    -0.06
    avers
    -0.06
    avy
    -0.06
     pret
    -0.06
    armi
    -0.06
    æķĻèĤ²å®¶
    -0.06
    ÙĪØ·
    -0.06
    POSITIVE LOGITS
    ãĢįãĢģãĢĮ
    0.08
    itur
    0.08
    GBT
    0.08
    سÙĬر
    0.08
    ιε
    0.07
    `,`
    0.07
    izzi
    0.07
    kit
    0.07
    éªļ
    0.07
    人æīįæĭĽèģĺ
    0.07
    Activations Density 0.057%

    No Known Activations