© 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. 4470
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    Categ
    -0.07
    æĸ¹æ³ķè¿Ľè¡Į
    -0.07
     Nug
    -0.07
    çļĦæŶéĹ´åĨħ
    -0.07
    è¦ģæ±Ĥè¿Ľè¡Į
    -0.07
    spre
    -0.07
    alise
    -0.07
    elige
    -0.07
    åѦåı²
    -0.07
    ç½ijç«Ļé¦ĸ页
    -0.07
    POSITIVE LOGITS
    rien
    0.07
    ä¹ĭä¸Ģ
    0.06
    èIJ©
    0.06
    å½Ĵ
    0.06
    èĬ¸
    0.06
     bombing
    0.06
     pil
    0.06
    zyman
    0.06
     ext
    0.06
    hips
    0.06
    Activations Density 0.026%

    No Known Activations