© 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. 29594
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation sequence

    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
    åĬłåħ³æ³¨
    -0.07
    Ø´Ùħ
    -0.06
    ès
    -0.06
    odar
    -0.06
    fel
    -0.06
    rots
    -0.06
     paras
    -0.06
     skoro
    -0.06
    eci
    -0.06
    ç¼ĵ
    -0.06
    POSITIVE LOGITS
    dney
    0.08
    çģ«æĬĬ
    0.08
    Href
    0.08
    人æĦı
    0.08
    ç¼Ī
    0.08
    ä¸½å¨ľ
    0.07
    Strip
    0.07
    abra
    0.07
    å¿ĹåĪļ
    0.07
    elight
    0.07
    Activations Density 0.010%

    No Known Activations