© 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. 51090
    Prev
    Next
    INDEX
    Explanations

    magnetic permeability

    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
    è½´è·Ŀ
    -0.08
    åĬłè½½ä¸Ń
    -0.08
    शन
    -0.08
    ä¸įæį¢
    -0.07
    æĶ¾æħ¢
    -0.07
    cono
    -0.07
    以赴
    -0.07
    iones
    -0.07
    æıIJç¥ŀ
    -0.07
    /autoload
    -0.07
    POSITIVE LOGITS
     shielding
    0.09
     shields
    0.09
     shield
    0.08
    åĨħéĥ¨
    0.07
    å±ıèĶ½
    0.07
     surfaces
    0.07
     internal
    0.07
    _touch
    0.07
    æ¶Ĥ
    0.07
    éļĶæĸŃ
    0.07
    Activations Density 0.003%

    No Known Activations