© 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. 16061
    Prev
    Next
    INDEX
    Explanations

    device uno

    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
    åĮ
    -0.07
    ãĥĥãĤ·
    -0.07
    ynt
    -0.07
    _Panel
    -0.07
    zec
    -0.07
    ardy
    -0.07
    nior
    -0.07
    кладÑĭ
    -0.07
    åĽ½æ°ijç»ıæµİ
    -0.06
    stime
    -0.06
    POSITIVE LOGITS
    åıĬéħįå¥Ĺ
    0.11
    æľ¬èº«
    0.10
    åıĬåħ¶
    0.10
    åıĬ
    0.10
     itself
    0.10
    åıĬ缸åħ³
    0.10
     indire
    0.09
    åĴĮåħ¶
    0.09
     indirectly
    0.09
    æĪĸåħ¶
    0.09
    Activations Density 0.466%

    No Known Activations