© 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. 21481
    Prev
    Next
    INDEX
    Explanations

    repetition, repeat, concatenate

    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
     convertible
    -0.07
    ä¸ī级
    -0.07
     вал
    -0.07
     Associated
    -0.07
    éĽ·é¸£
    -0.06
    ardt
    -0.06
    gett
    -0.06
    asar
    -0.06
    éĩijåĪ¸
    -0.06
    央è§Ĩæĸ°éĹ»
    -0.06
    POSITIVE LOGITS
    concat
    0.12
    æĭ¼æİ¥
    0.12
     concaten
    0.12
    éĩįå¤į
    0.12
     repetition
    0.11
     repetitions
    0.11
     concatenate
    0.11
     concatenated
    0.11
    åı¦ä¸ĢåįĬ
    0.11
    .repeat
    0.10
    Activations Density 0.020%

    No Known Activations