© 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. 48609
    Prev
    Next
    INDEX
    Explanations

    is compact, cyclic

    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
    itech
    -0.07
    Å¡n
    -0.07
    minos
    -0.07
    ugno
    -0.07
    ıŁ
    -0.07
    ãĥĿãĥ³
    -0.07
    estes
    -0.07
    isphere
    -0.07
    奥åĪ©
    -0.07
    ambo
    -0.07
    POSITIVE LOGITS
    berger
    0.08
    .easing
    0.07
    对ä¸Ĭè¿°
    0.07
     Klan
    0.07
     assumed
    0.07
    uzzi
    0.07
    èµ·ä½ľçĶ¨
    0.07
    对è¿Ļ个
    0.07
    æĹ¥çĽĬ
    0.06
     assumption
    0.06
    Activations Density 0.004%

    No Known Activations