© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24563
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    çĶ¨æĪ·ä¸Ĭä¼ł
    -0.08
    onis
    -0.07
    esson
    -0.07
    åħ¨éĥ¨è¯Ħ论
    -0.07
    讲ä¹ī
    -0.07
    uib
    -0.07
    ovia
    -0.07
    ipes
    -0.07
    åĬłçıŃåĬłçĤ¹
    -0.07
     jam
    -0.07
    POSITIVE LOGITS
     questions
    0.15
     unanswered
    0.15
     Questions
    0.14
    ä¸ĢéĹ®
    0.14
    questions
    0.14
    å°±éĹ®
    0.12
     asking
    0.12
    æıIJéĹ®
    0.11
    éĹ®
    0.11
    Questions
    0.11
    Activations Density 0.295%

    No Known Activations