© 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. 29410
    Prev
    Next
    INDEX
    Explanations

    expressions of repetition

    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
    olda
    -0.07
    é«ĺ人
    -0.07
    lay
    -0.07
    flo
    -0.07
    erva
    -0.07
    ĭ
    -0.06
    ãĤŃãĥ£ãĥ³
    -0.06
    大åħ¨
    -0.06
     رÙģ
    -0.06
    éı
    -0.06
    POSITIVE LOGITS
     again
    0.11
    again
    0.11
    Again
    0.09
     Again
    0.09
    åıĪä¸Ģ次
    0.09
     опÑıÑĤÑĮ
    0.09
     AGAIN
    0.09
    å¾Ĺä¸įåĪ°
    0.08
    åıĪæĺ¯
    0.08
    sons
    0.08
    Activations Density 0.040%

    No Known Activations