© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15153
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and 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
    åĪļéľĢ
    -0.07
    çĻ¾åIJį
    -0.06
    INGTON
    -0.06
    ALLEL
    -0.06
    insk
    -0.06
    æĪĸåħ¶
    -0.06
    serter
    -0.06
    çľģæ²¹
    -0.06
    بÙĬا
    -0.06
    ,ll
    -0.06
    POSITIVE LOGITS
    å±±æ¹ĸ
    0.08
    ä¸Ģæĸ°
    0.07
    ắng
    0.07
    áte
    0.07
    otra
    0.07
    èijĽ
    0.06
    æľĪ份å¼Ģå§ĭ
    0.06
    hea
    0.06
    ofi
    0.06
    lessly
    0.06
    Activations Density 0.095%

    No Known Activations