© 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. 28850
    Prev
    Next
    INDEX
    Explanations

    adsorption/BET

    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
    otomy
    -0.08
    oten
    -0.07
    izu
    -0.07
    à¸ľà¹Īา
    -0.07
     cables
    -0.07
    çŃĭ
    -0.07
     cutting
    -0.07
     cut
    -0.07
     patched
    -0.07
     nicknamed
    -0.06
    POSITIVE LOGITS
     ads
    0.11
     Ads
    0.10
    åIJ¸éĻĦ
    0.10
    Ads
    0.10
     occupancy
    0.08
    ommer
    0.08
    åIJ¸
    0.08
    Mgr
    0.08
    èĪĶ
    0.08
     вакан
    0.07
    Activations Density 0.022%

    No Known Activations