© 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. 57931
    Prev
    Next
    INDEX
    Explanations

    repeatedly, 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
    sez
    -0.08
    ละ
    -0.07
    åIJĪä½µ
    -0.07
    æµ®
    -0.07
    [class
    -0.07
    cen
    -0.07
    èįŁ
    -0.07
    æŀ¶ç©º
    -0.07
    ازÙĩ
    -0.07
    ¿
    -0.07
    POSITIVE LOGITS
     repet
    0.08
    è¾Ĺ转
    0.08
    elok
    0.07
    ç´«èįĨ
    0.07
    æī
    0.07
    indh
    0.07
     ripet
    0.07
     berulang
    0.07
     repeatedly
    0.06
    屡次
    0.06
    Activations Density 0.010%

    No Known Activations