© 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. 14575
    Prev
    Next
    INDEX
    Explanations

    few, fewer, and related words

    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
    essant
    -0.09
    uito
    -0.09
    rific
    -0.09
     ulang
    -0.09
    krieg
    -0.09
    aison
    -0.09
    rauch
    -0.09
    Ļ
    -0.09
    kits
    -0.09
    ziali
    -0.09
    POSITIVE LOGITS
    ened
    0.12
    ä¹ĭåıĪ
    0.10
    ening
    0.09
    ness
    0.08
    ive
    0.08
    à¹Ĩ
    0.08
    al
    0.07
    (er
    0.07
     hụt
    0.07
    mals
    0.07
    Activations Density 0.022%

    No Known Activations