© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61611
    Prev
    Next
    INDEX
    Explanations

    garbled text and punctuation

    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
    èĥ½è¯´
    -0.07
    说
    -0.06
    enos
    -0.06
    isms
    -0.06
     Alvarez
    -0.06
    oriously
    -0.06
    _managed
    -0.06
    ìŀ¥
    -0.06
    æıIJ
    -0.06
    chio
    -0.06
    POSITIVE LOGITS
    é«ĺ度çļĦ
    0.08
    åĪĩå®ŀæĬĬ
    0.07
    çĥŃ泪
    0.07
    åĪ·åŃIJ
    0.07
    èĩªæĭħ
    0.07
    abis
    0.07
    çļĦé«ĺ度
    0.07
    abic
    0.07
    .opensource
    0.07
    arei
    0.07
    Activations Density 0.015%

    No Known Activations