© 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. 17345
    Prev
    Next
    INDEX
    Explanations

    Home links and breadcrumbs

    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
    åı£åŃIJ
    -0.06
     hold
    -0.06
    matic
    -0.06
    å³Ļ
    -0.06
    éĿ¢è®®
    -0.06
    两åı°
    -0.06
    çļĦçĬ¶åĨµ
    -0.06
     Hold
    -0.06
    itational
    -0.06
     Marsh
    -0.06
    POSITIVE LOGITS
    ãģ«æĪ»ãĤĭ
    0.10
    breadcrumb
    0.09
    éĹľ
    0.08
    elts
    0.08
    éĸ¢
    0.08
    导èĪª
    0.08
    /browse
    0.08
     RETURN
    0.08
    imina
    0.08
    ãģ«æĪ»
    0.07
    Activations Density 0.092%

    No Known Activations