© 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. 27659
    Prev
    Next
    INDEX
    Explanations

    simulation and practice

    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
    åĬłçıŃåĬłçĤ¹
    -0.07
     surveyed
    -0.07
     CONTRIBUT
    -0.07
    è°ĥæŁ¥ç»ĵæŀľ
    -0.07
    leb
    -0.07
    è¸Ĭ
    -0.07
    _MOD
    -0.06
    -alist
    -0.06
    åīį线
    -0.06
    blatt
    -0.06
    POSITIVE LOGITS
    ç»ĥä¹ł
    0.15
    模æĭŁ
    0.14
    æ¼Ķç»ĥ
    0.14
     simulated
    0.13
     simulate
    0.13
    ç»ĥ
    0.13
     exercises
    0.12
    å®ŀæĪĺ
    0.12
     simulation
    0.12
    模æĵ¬
    0.12
    Activations Density 0.115%

    No Known Activations