© 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. 22234
    Prev
    Next
    INDEX
    Explanations

    magnetic fields and guiding light

    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
    éĽĨæķ£
    -0.08
    lix
    -0.07
    å£ķ
    -0.07
     dul
    -0.07
    象çīĻ
    -0.07
    misc
    -0.07
    á»įt
    -0.07
    aise
    -0.06
    æĻ
    -0.06
    oplay
    -0.06
    POSITIVE LOGITS
    -dominated
    0.08
     Wire
    0.08
     wire
    0.08
    Stored
    0.07
     lightning
    0.07
     magnetic
    0.07
    genesis
    0.07
    å±Ģåľ°
    0.07
    åĪ©æµ¦
    0.07
    ravi
    0.07
    Activations Density 0.009%

    No Known Activations