© 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. 9465
    Prev
    Next
    INDEX
    Explanations

    verb + object phrase

    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
    byt
    -0.07
    æĦıæĸĻ
    -0.07
    abat
    -0.07
    iran
    -0.06
    Ñģле
    -0.06
    äºĨæī¿
    -0.06
    à¸Ļà¹Īา
    -0.06
    igue
    -0.06
    亦çĦ¶
    -0.06
    æĥ³ä¸įåĪ°
    -0.06
    POSITIVE LOGITS
    åıĪæĢķ
    0.12
     möglichst
    0.11
    ä½ĨåıĪ
    0.10
     someday
    0.10
     graag
    0.09
    åıĪæĥ³
    0.09
     непÑĢеменно
    0.09
    çĤ¹ä»Ģä¹Ī
    0.08
    æľīä¸Ģçķª
    0.08
     à¸Ńยาà¸ģ
    0.08
    Activations Density 0.864%

    No Known Activations