© 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. 26227
    Prev
    Next
    INDEX
    Explanations

    production process

    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
     clutter
    -0.07
    æľªç»ıåħģ许
    -0.07
     elic
    -0.06
     Druid
    -0.06
     caregiver
    -0.06
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    -0.06
    åªĽ
    -0.06
     paranormal
    -0.06
    allax
    -0.06
    èĮĹ
    -0.06
    POSITIVE LOGITS
    åİŁæĸĻ
    0.11
     profitability
    0.11
    çĶŁäº§çļĦ
    0.10
    æ³ķåĪ¶
    0.09
     profitable
    0.09
    çĶŁäº§åĩº
    0.09
    éĤ£åº§
    0.09
    åī¯äº§åĵģ
    0.09
     industrial
    0.09
     downstream
    0.09
    Activations Density 0.279%

    No Known Activations