© 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. 42644
    Prev
    Next
    INDEX
    Explanations

    text after "From", "Therefore", "Meeting", "Please"

    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
    bidden
    -0.11
    enticate
    -0.11
    oretical
    -0.10
    ../../../
    -0.10
    ially
    -0.09
    ernel
    -0.09
    INCT
    -0.09
     Äijặn
    -0.09
    ting
    -0.08
    å¤ļãģĦ
    -0.08
    POSITIVE LOGITS
    er
    0.14
    à±ģ
    0.13
    о
    0.12
    د
    0.10
    çĦ¶å¤§
    0.09
    инÑĭ
    0.09
    ãģĬ
    0.09
    à¸Ļิà¸ĺิ
    0.09
    erer
    0.09
    o
    0.09
    Activations Density 0.133%

    No Known Activations