© 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. 4387
    Prev
    Next
    INDEX
    Explanations

    legal citation abbreviations

    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
    -0.10
     [âĢ¦]
    -0.08
    -0.08
     recieved
    -0.07
     [âĢ¦
    -0.07
     –
    -0.07
    strup
    -0.07
     (âĢ¦)
    -0.07
    ´t
    -0.07
     unins
    -0.07
    POSITIVE LOGITS
    æĥŁä¸Ģ
    0.07
    ä¸įèĭŁ
    0.07
    æ¸Ĭ
    0.07
    å®ļæł¼
    0.07
    ashes
    0.07
    ìŁģ
    0.07
    ä¸Ģä¸Ģ
    0.07
    çļĦåIJį
    0.07
    éĩĬä¹ī
    0.07
    chu
    0.06
    Activations Density 0.015%

    No Known Activations