© 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. 62897
    Prev
    Next
    INDEX
    Explanations

    any particular purpose

    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
    blings
    -0.09
     bè
    -0.09
    bour
    -0.09
    hoff
    -0.08
    chin
    -0.08
    strings
    -0.08
     pupper
    -0.08
    posables
    -0.07
    æīĢ欲
    -0.07
    大年
    -0.07
    POSITIVE LOGITS
     specific
    0.12
    çī¹å®ļçļĦ
    0.11
    çī¹å®ļ
    0.11
     particular
    0.11
    æĸĩ件æĪĸ
    0.10
     somehow
    0.10
    æŁIJç§į
    0.09
     particolare
    0.09
     خاصÛĮ
    0.09
     tertentu
    0.09
    Activations Density 0.016%

    No Known Activations