© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4432
    Prev
    Next
    INDEX
    Explanations

    words after "the" or "a"

    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
    {/
    -0.08
    tsx
    -0.07
    xca
    -0.07
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.07
    anyl
    -0.07
    VERS
    -0.07
    cott
    -0.07
    à¦Ĥশ
    -0.07
    ters
    -0.07
    VERSE
    -0.07
    POSITIVE LOGITS
    Ł
    0.06
    attan
    0.06
    cek
    0.06
    пÑĤи
    0.06
    æ¸ħçļĦ
    0.05
    aging
    0.05
    archical
    0.05
    áĢĬáĢºáĢ¸
    0.05
    çļĦæīĢæľī
    0.05
    ç¹ģèĤ²
    0.05
    Activations Density 1.990%

    No Known Activations