© 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. 16148
    Prev
    Next
    INDEX
    Explanations

    array part, static cell, before details

    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
    ignan
    -0.09
    æ·¡åĮĸ
    -0.07
    elm
    -0.07
    ÐĴÐĶ
    -0.07
    probe
    -0.07
    é£İéĻ©ä¿¡æģ¯
    -0.07
    utow
    -0.07
    _NOW
    -0.07
    æ¤
    -0.07
    èĮ«èĮ«
    -0.07
    POSITIVE LOGITS
    缴è§Ĩ
    0.09
    缴æİ¥
    0.08
     Schon
    0.08
     outside
    0.08
    åı¯ä»¥çĽ´æİ¥
    0.07
    缴åĩ»
    0.07
    å°ıéĥ¨åĪĨ
    0.07
    缴å±ŀ
    0.07
     handle
    0.07
     outright
    0.07
    Activations Density 0.037%

    No Known Activations