© 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. 46209
    Prev
    Next
    INDEX
    Explanations

    Greek letters and scientific 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
    ัà¸Ļ
    -0.06
    _kwargs
    -0.06
    ely
    -0.06
    asty
    -0.06
    czy
    -0.06
    çĭIJ
    -0.06
    媳å¦ĩ
    -0.06
    è·¯å°ıåѦ
    -0.06
     olmayan
    -0.06
    ayar
    -0.06
    POSITIVE LOGITS
    #ad
    0.08
     wobei
    0.08
    enga
    0.07
    åħ¶ä¸Ń
    0.07
    ना
    0.07
    ("."
    0.07
    .carousel
    0.07
    igne
    0.07
    å°±çľŁçļĦ
    0.07
    è¿Ļ个éģĵçIJĨ
    0.07
    Activations Density 0.006%

    No Known Activations