© 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. 29375
    Prev
    Next
    INDEX
    Explanations

    object representation serialization

    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
    ondes
    -0.07
    odzi
    -0.07
    isseur
    -0.07
    imeo
    -0.07
     Pedi
    -0.07
    )._
    -0.06
    attan
    -0.06
    legs
    -0.06
    _Pin
    -0.06
    Pin
    -0.06
    POSITIVE LOGITS
    天河
    0.08
     Ersatz
    0.07
     scientific
    0.07
    abb
    0.07
    _listing
    0.07
    æľº
    0.07
    åħ´åįİ
    0.07
    带éĺŁ
    0.07
    符
    0.07
    å·©
    0.06
    Activations Density 0.020%

    No Known Activations