© 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. 20428
    Prev
    Next
    INDEX
    Explanations

    sequences of 'l'

    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
     both
    -0.08
     either
    -0.07
    both
    -0.07
     Both
    -0.07
    Both
    -0.06
    ist
    -0.06
    -0.06
     (
    -0.06
     оба
    -0.06
    两èĢħ
    -0.06
    POSITIVE LOGITS
    ?,?,?,?,
    0.12
    ?,?,
    0.10
    åIJĦè¡Į
    0.09
     dépl
    0.08
     Lò
    0.08
     ÐļÑĢаÑģи
    0.08
    óst
    0.08
     CURLOPT
    0.08
    ä»»ä½ķä¿Ŀè¯ģ
    0.08
    æĮĩ导建议
    0.08
    Activations Density 0.041%

    No Known Activations