© 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. 11694
    Prev
    Next
    INDEX
    Explanations

    measurement units

    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
    起家
    -0.07
    è¸Ĭ
    -0.07
    çĬ¹
    -0.07
     âĨij
    -0.07
    ierz
    -0.07
     '}
    -0.07
    -in
    -0.07
    borg
    -0.07
    aller
    -0.07
    owler
    -0.06
    POSITIVE LOGITS
    BlockSize
    0.08
    大约æľī
    0.07
    å¸Ĥåľºè§Ħ模
    0.07
    æĸĩ件大å°ı
    0.07
    ction
    0.06
    onal
    0.06
    CTS
    0.06
    ä¹ĭéĹ´çļĦè·Ŀ离
    0.06
    ucht
    0.06
    agna
    0.06
    Activations Density 0.166%

    No Known Activations