© 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. 20425
    Prev
    Next
    INDEX
    Explanations

    quoted text following quotes or parentheses

    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
     consum
    -0.07
    人çļĦçĶŁåij½
    -0.07
    离åIJĪ
    -0.07
    太çĽij
    -0.07
     agricole
    -0.07
    ='_
    -0.07
    gnore
    -0.07
    innacle
    -0.06
    ches
    -0.06
    æ¶Ī
    -0.06
    POSITIVE LOGITS
    наÑĢ
    0.08
    ä¸ĵæ¡Ī
    0.08
    .Contract
    0.07
    馨
    0.07
    å§ĭ
    0.06
     bre
    0.06
    inspect
    0.06
    ifikasi
    0.06
    èĬĿ
    0.06
     Done
    0.06
    Activations Density 0.028%

    No Known Activations