© 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. 28016
    Prev
    Next
    INDEX
    Explanations

    cycle or loop

    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
    lut
    -0.08
    à¸ĭีà¹Ī
    -0.07
    å¾Ĺå½ĵ
    -0.07
     Marin
    -0.07
     prem
    -0.07
    .deb
    -0.07
    代为
    -0.07
    lima
    -0.07
    è²»
    -0.06
    æĮĩå®ļåľ°çĤ¹
    -0.06
    POSITIVE LOGITS
    loop
    0.12
    (loop
    0.12
     loop
    0.12
    åĽŀè·¯
    0.12
     loops
    0.12
    -loop
    0.11
     looping
    0.10
    循çݯ
    0.10
    çݯ
    0.10
     LOOP
    0.10
    Activations Density 0.005%

    No Known Activations