© 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. 24251
    Prev
    Next
    INDEX
    Explanations

    chemical and composite matter

    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
    _blocking
    -0.08
    iscal
    -0.08
    Ñįй
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
     positioning
    -0.07
     dep
    -0.07
    å¾Ļ
    -0.07
     Rappel
    -0.07
    缸åħ³æݨèįIJ
    -0.07
    路交åıīåı£
    -0.07
    POSITIVE LOGITS
    åįģåħ¨
    0.08
    å¦Ĥæŀľä¸Ģ个
    0.07
    ChangeEvent
    0.07
    éĿŀçī©è´¨
    0.07
     chemical
    0.07
    åĬ¨æ¤įçī©
    0.07
    chemical
    0.07
    å¤ļ姿
    0.07
    äºĭçī©çļĦ
    0.07
    äºĭçī©
    0.07
    Activations Density 0.001%

    No Known Activations