© 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. 11089
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific noun phrases

    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
     remer
    -0.07
    çļĦæŶåĢĻåı¯ä»¥
    -0.07
    brahim
    -0.07
     Vu
    -0.07
    lina
    -0.06
    à¹Īà¸Ńย
    -0.06
    ebro
    -0.06
     demais
    -0.06
    çļĦæŶåĢĻä¸Ģå®ļè¦ģ
    -0.06
    ynd
    -0.06
    POSITIVE LOGITS
    zez
    0.07
    ieÃŁ
    0.07
    agung
    0.07
    è¡·å¿ĥçļĦ
    0.07
    åľ¨æīĢ
    0.06
    ibu
    0.06
    Ĭ
    0.06
    èĬ·
    0.06
    -intensive
    0.06
    çĦ¶åIJİåĨį
    0.06
    Activations Density 0.452%

    No Known Activations