© 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. 61172
    Prev
    Next
    INDEX
    Explanations

    review article

    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
    ä»Ģä¹Īåı«
    -0.08
     Liter
    -0.07
    åıªæıIJä¾Ľ
    -0.07
    elaar
    -0.07
    å¾Ĵ
    -0.07
    æĦıæĮĩ
    -0.07
    ä½łåıªè¦ģ
    -0.07
    ogui
    -0.07
    ловÑĸ
    -0.07
    çĺ©
    -0.07
    POSITIVE LOGITS
    apse
    0.07
    aker
    0.07
    à¶Ń
    0.07
    rending
    0.07
    alani
    0.07
    mtime
    0.07
     contund
    0.07
    ouched
    0.06
    確
    0.06
    akedown
    0.06
    Activations Density 0.016%

    No Known Activations