© 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. 57450
    Prev
    Next
    INDEX
    Explanations

    cell wall

    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
     inputs
    -0.08
    åľŁæĸ¹
    -0.07
    æijĨåľ¨
    -0.07
    omie
    -0.07
    æŀĿèĬ±
    -0.07
    steam
    -0.07
    æij¸åºķ
    -0.07
    æµģæ°ĵ
    -0.07
     Warszaw
    -0.07
    iski
    -0.07
    POSITIVE LOGITS
    åĿļ飧
    0.12
    硬åĮĸ
    0.10
    è´¨
    0.09
    åĿļ硬
    0.09
    çļĦç»ĵæŀĦ
    0.09
    硬度
    0.09
     parchment
    0.08
    æĶ¯æĴij
    0.08
    å¤ĸå±Ĥ
    0.08
    碳éħ¸éĴĻ
    0.08
    Activations Density 0.076%

    No Known Activations