© 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. 23017
    Prev
    Next
    INDEX
    Explanations

    temporal sequencing and control

    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
    —or
    -0.08
    è¿ĺåħ·æľī
    -0.07
    æĪĸå°Ĩ
    -0.07
    è¿ĺæĺ¯åľ¨
    -0.07
     برگ
    -0.07
    ä»ĸãģ«ãĤĤ
    -0.07
    ä¸ľè¥¿
    -0.07
    agit
    -0.07
    ael
    -0.07
    åĢĻéĢī
    -0.07
    POSITIVE LOGITS
    jó
    0.07
     cẩn
    0.07
    áĢ±áĢ¬áĢĦáĢº
    0.07
    omp
    0.07
     thereafter
    0.07
    èĶ»
    0.06
     coc
    0.06
     afterwards
    0.06
     beforehand
    0.06
     afterward
    0.06
    Activations Density 0.178%

    No Known Activations