© 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. 33085
    Prev
    Next
    INDEX
    Explanations

    explicitly or directly

    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
    ç¯Ŀ
    -0.08
    otec
    -0.07
    åħĭåħ°
    -0.07
    onel
    -0.07
    èĬ¹
    -0.07
    _consts
    -0.07
    å®
    -0.07
    .raise
    -0.06
    áĥ¦
    -0.06
    onse
    -0.06
    POSITIVE LOGITS
     explicitly
    0.28
    explicit
    0.26
    Explicit
    0.26
     explicit
    0.25
     Explicit
    0.23
     directly
    0.23
    æĺİç¡®
    0.22
    缴æİ¥
    0.22
    缴æİ¥çļĦ
    0.21
    æĺİç¡®çļĦ
    0.21
    Activations Density 0.211%

    No Known Activations