© 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. 25782
    Prev
    Next
    INDEX
    Explanations

    duplicates, repeats, and instances

    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
    _RUNTIME
    -0.07
    åħ¨åŁŁ
    -0.07
    æĿİå¿Ĺ
    -0.07
    olik
    -0.06
    _generation
    -0.06
    ighb
    -0.06
    åįĥéĩĮ
    -0.06
    åħ¨æµģç¨ĭ
    -0.06
    éĢĨè¡Į
    -0.06
    igne
    -0.06
    POSITIVE LOGITS
    éĩįå¤į
    0.13
     duplicates
    0.11
     repeats
    0.11
     repetition
    0.11
    .dup
    0.11
    éĩįè¤ĩ
    0.11
    å¤įåĪ¶
    0.11
    Dup
    0.10
     repetitions
    0.10
    Duplicates
    0.10
    Activations Density 0.048%

    No Known Activations