© 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. 42290
    Prev
    Next
    INDEX
    Explanations

    actions or events

    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
    ç¹ģ
    -0.08
    ijin
    -0.07
    arming
    -0.07
    enhagen
    -0.07
    anguage
    -0.07
    èĪ¬çļĦ
    -0.07
    ην
    -0.07
    oader
    -0.07
    tbl
    -0.07
    ovÄĽ
    -0.07
    POSITIVE LOGITS
    次æķ°
    0.08
    æŃ´
    0.08
    ouch
    0.07
     подÑĢÑıд
    0.07
    åºıåı·
    0.07
    alis
    0.07
    MIT
    0.07
    bach
    0.06
    产åīį
    0.06
    orat
    0.06
    Activations Density 0.018%

    No Known Activations