© 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. 18101
    Prev
    Next
    INDEX
    Explanations

    -related suffixes / -associated suffixes

    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
     anyway
    -0.07
    aran
    -0.07
    ç§ijéķ¿
    -0.06
    zol
    -0.06
    º¼
    -0.06
     sticks
    -0.06
    å¤§éĽ¨
    -0.06
    åIJĪéĻ¢
    -0.06
    大路
    -0.06
    ikir
    -0.06
    POSITIVE LOGITS
    -themed
    0.10
    ä½ľä¸ºä¸Ģç§į
    0.09
    ä½ľä¸ºä¸Ģ项
    0.09
    çŃīçī¹æ®Ĭ
    0.09
    æĪIJ为ä¸Ģç§į
    0.08
    -associated
    0.08
    -related
    0.08
    -induced
    0.07
    è¿ĻäºĭåĦ¿
    0.07
    idon
    0.07
    Activations Density 0.364%

    No Known Activations