© 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. 21697
    Prev
    Next
    INDEX
    Explanations

    limiting factors or dominant conditions

    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
    ç¥ŀä¹ĭ
    -0.08
    zus
    -0.08
    pla
    -0.08
     ÑĩаÑģÑĤиÑĩ
    -0.07
    çī¹åĪ«çļĦ
    -0.07
     immedi
    -0.07
    eward
    -0.07
    å¾ĢæĿ¥
    -0.07
    ardino
    -0.07
    íĹĺ
    -0.07
    POSITIVE LOGITS
    çĵ¶é¢Ī
    0.15
     bottleneck
    0.13
     bott
    0.11
    çŁŃæĿ¿
    0.11
    åĪ¶çº¦
    0.09
     dominant
    0.09
     limiting
    0.09
     Bott
    0.09
     dominate
    0.08
     dominated
    0.08
    Activations Density 0.060%

    No Known Activations