© 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. 3223
    Prev
    Next
    INDEX
    Explanations

    long as / distance / -term

    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
    Åijl
    -0.10
    macher
    -0.09
    ramid
    -0.08
    æĪIJç«ł
    -0.08
    ergestellt
    -0.08
     ulang
    -0.08
    ullah
    -0.08
    æŃ¤èµ·
    -0.08
     ÐŁÐ¾Ð¿ÑĢо
    -0.08
    ingatkan
    -0.08
    POSITIVE LOGITS
    evity
    0.14
    -awaited
    0.13
    itud
    0.13
     serialVersionUID
    0.11
    -lived
    0.11
    itudes
    0.10
    ening
    0.10
    кÑĢаÑĤно
    0.10
    ish
    0.09
    ãģĺãģ¦
    0.09
    Activations Density 0.081%

    No Known Activations