© 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. 55775
    Prev
    Next
    INDEX
    Explanations

    stripe spacing features

    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
    issy
    -0.07
    缴æİ¥è¿Ľåħ¥
    -0.07
    å¾®éĩı
    -0.07
    åĨ¶
    -0.07
    æģ
    -0.07
    å¤ļåħĥ
    -0.06
    å¿ħè¦ģæŶ
    -0.06
     Cannon
    -0.06
     mainstream
    -0.06
    schuss
    -0.06
    POSITIVE LOGITS
    éĹ´è·Ŀ
    0.10
     spacing
    0.10
     alternating
    0.09
    stripe
    0.09
    Spacing
    0.09
    æĿ¡çº¹
    0.08
     stripes
    0.08
    км
    0.08
    -spacing
    0.08
     fringe
    0.08
    Activations Density 0.010%

    No Known Activations