© 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. 8149
    Prev
    Next
    INDEX
    Explanations

    Michael Arbuthnot, Kurt Sanderling

    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
    enk
    -0.07
    å®ļä¹īçļĦ
    -0.07
    å¤ĸåĽ½è¯Ń
    -0.06
    ä¸įè¨Ģ
    -0.06
    æ°¸è¿ľçļĦ
    -0.06
    ride
    -0.06
    ou
    -0.06
     Lie
    -0.06
    !!,
    -0.06
    umm
    -0.06
    POSITIVE LOGITS
    对åİŁåijĬ
    0.08
    æ§ĺ
    0.08
    elda
    0.08
    دة
    0.07
    atkan
    0.07
    èĸ°
    0.07
    atee
    0.07
    ebol
    0.07
    devil
    0.07
    ะ
    0.07
    Activations Density 0.057%

    No Known Activations