© 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. 16208
    Prev
    Next
    INDEX
    Explanations

    first part

    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
    究
    -0.08
     ÑĦÑĥÑĢ
    -0.08
    suit
    -0.08
    åľ¨å®ĮæĪIJ
    -0.07
    vento
    -0.07
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    å¤Ħç½ļéĩij
    -0.07
     cosidd
    -0.07
    ìĿ´ëĿ¼ëıĦ
    -0.07
    çĶ³
    -0.07
    POSITIVE LOGITS
    第ä¸Ģ个
    0.06
    zil
    0.06
     first
    0.06
    :first
    0.06
    ypo
    0.06
    éĤ£åĿĹ
    0.06
    第ä¸ĢæĿ¡
    0.06
    zah
    0.06
    λί
    0.06
    elder
    0.06
    Activations Density 0.014%

    No Known Activations