© 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. 16586
    Prev
    Next
    INDEX
    Explanations

    square roots and mathematical expressions

    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
    å±ĪæĮĩ
    -0.08
    ableObject
    -0.08
    åħ·åIJĪ
    -0.08
    entially
    -0.07
    ToDevice
    -0.07
    egin
    -0.07
    meen
    -0.07
    indet
    -0.07
    anyol
    -0.07
    éĿŀ常å¤ļ
    -0.07
    POSITIVE LOGITS
    ...]
    0.08
     +
    0.07
    浩
    0.07
    fat
    0.07
    ØŃÙĪ
    0.07
    hay
    0.07
    chts
    0.06
     farsi
    0.06
    ãĥĹãĥ©ãĤ¹
    0.06
    ίαÏĤ
    0.06
    Activations Density 0.002%

    No Known Activations