© 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. 48492
    Prev
    Next
    INDEX
    Explanations

    cyclic order or rotations

    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
     rusty
    -0.07
    åħ¬å®īåİħ
    -0.07
    æ´ģåħ·
    -0.06
    ī
    -0.06
    æİĸ
    -0.06
     CONSEQUENTIAL
    -0.06
    追溯
    -0.06
    é¸¡æ¯Ľ
    -0.06
    Bracket
    -0.06
    alan
    -0.06
    POSITIVE LOGITS
    循çݯ
    0.10
    åij¨æľŁ
    0.10
     cycle
    0.09
    åij¨æľŁæĢ§
    0.09
    循çĴ°
    0.09
     cyclic
    0.09
    -cycle
    0.09
    .cycle
    0.09
    è½®åĽŀ
    0.09
    cycle
    0.08
    Activations Density 0.009%

    No Known Activations