© 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. 1534
    Prev
    Next
    INDEX
    Explanations

    following `_` or `;`

    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
    och
    -0.08
    æĶĢ
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.06
    çIJĥ
    -0.06
    çĺŁ
    -0.06
     Vi
    -0.06
    çľ¼
    -0.06
    èĵĭ
    -0.06
    ory
    -0.06
    çĽĸ
    -0.06
    POSITIVE LOGITS
    åĭ¤åѦ
    0.09
    Ī¬
    0.09
    Dig
    0.08
    лак
    0.07
    inkel
    0.07
    ($)
    0.07
    ÙĬÙħÙĬ
    0.07
    æĬĬè¿Ļ个
    0.07
    æĭįæĪı
    0.07
     dbg
    0.07
    Activations Density 0.512%

    No Known Activations