© 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. 50292
    Prev
    Next
    INDEX
    Explanations

    vacuum related terms

    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
    ValuePair
    -0.09
     volna
    -0.09
    alam
    -0.08
    maÃŁen
    -0.08
    lem
    -0.08
    gebn
    -0.08
    bach
    -0.08
    abyrin
    -0.08
    trand
    -0.07
    anou
    -0.07
    POSITIVE LOGITS
    uum
    0.08
    æ·±å¤Ħ
    0.08
    èį¡èį¡
    0.07
    iliar
    0.07
    ç©´
    0.07
    æ»ĵ
    0.07
    arella
    0.07
    ķ
    0.07
    Õ¡Õµ
    0.07
    éļĻ
    0.07
    Activations Density 0.014%

    No Known Activations