© 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. 64922
    Prev
    Next
    INDEX
    Explanations

    voltage clamp, exactly, notify, async connect, object tree, https

    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
    å°¾
    -0.08
    oland
    -0.08
    .sh
    -0.07
    Ñģкоп
    -0.07
    arez
    -0.07
    erland
    -0.06
     copa
    -0.06
    å½±è§Ĩ
    -0.06
    ires
    -0.06
    åĽ½äºº
    -0.06
    POSITIVE LOGITS
    åĥı个
    0.08
    BTN
    0.07
    usy
    0.07
    ilding
    0.07
    ç«ĭåĪ»å°±
    0.07
    ieber
    0.07
    KHR
    0.06
    è¿Ļ让æĪij
    0.06
    åīįè¨Ģ
    0.06
    æ½ĩæ¹ĺ
    0.06
    Activations Density 0.411%

    No Known Activations