© 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. 14818
    Prev
    Next
    INDEX
    Explanations

    filling, occupation, doping

    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
    jenis
    -0.08
     NotImplemented
    -0.08
     Prat
    -0.07
    istra
    -0.07
    ä¼Ł
    -0.07
    åĺ´è¾¹
    -0.07
     strerror
    -0.07
    宽é«ĺ
    -0.07
    leistung
    -0.07
    Haus
    -0.07
    POSITIVE LOGITS
    填满
    0.10
    å¡«åħħ
    0.09
     occupation
    0.08
     заполнениÑı
    0.08
    fills
    0.08
     Occupation
    0.08
    已满
    0.08
     filling
    0.08
    åįłæį®
    0.08
    .fill
    0.08
    Activations Density 0.002%

    No Known Activations