© 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. 23206
    Prev
    Next
    INDEX
    Explanations

    uranium dioxide, plutonium dioxide

    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
    igi
    -0.08
    icast
    -0.07
    çļĭ
    -0.07
    quil
    -0.07
    set
    -0.06
    igo
    -0.06
    igit
    -0.06
    ce
    -0.06
    emark
    -0.06
     ÐĹаÑī
    -0.06
    POSITIVE LOGITS
    onium
    0.08
    ônio
    0.07
    -black
    0.07
    åij¼åĴĮ浩çī¹
    0.07
    ä¸ĢæĿ¡è¡Ĺ
    0.07
    åĬŁåĭĭ
    0.07
     Idaho
    0.07
    umon
    0.07
    稳
    0.07
    oxide
    0.07
    Activations Density 0.003%

    No Known Activations