© 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. 24361
    Prev
    Next
    INDEX
    Explanations

    specific/certain/particular modifier

    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
    æıIJè¦ģ
    -0.08
     belangrijkste
    -0.08
     meisten
    -0.07
    ides
    -0.07
    åħ±åĪĨ
    -0.07
    kaan
    -0.07
    ¥
    -0.07
    åħ¨æĹł
    -0.07
     lẫn
    -0.07
    ¹
    -0.07
    POSITIVE LOGITS
    çī¹å®ļçļĦ
    0.14
    çī¹å®ļ
    0.14
     specific
    0.11
    çī¹å®ļãģ®
    0.10
     tertentu
    0.10
     particular
    0.09
    specific
    0.09
     íĬ¹ìłķ
    0.09
     certain
    0.08
     bestimmten
    0.08
    Activations Density 0.117%

    No Known Activations