© 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. 17783
    Prev
    Next
    INDEX
    Explanations

    code comments /** or /*

    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
    Ñĩей
    -0.08
    .appendTo
    -0.08
    inique
    -0.08
    nik
    -0.07
    rica
    -0.07
    åįĥ
    -0.07
    icin
    -0.07
    à¤Ĥà¤Ł
    -0.07
    riff
    -0.07
    ContentLoaded
    -0.07
    POSITIVE LOGITS
    è¿ĩå°ı
    0.07
    以赴
    0.07
    unu
    0.06
    åĮĸ管çIJĨ
    0.06
     ed
    0.06
     Mar
    0.06
    atoria
    0.06
    {/
    0.06
     Under
    0.06
    åľ¨çĻ½
    0.06
    Activations Density 0.002%

    No Known Activations