© 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. 8840
    Prev
    Next
    INDEX
    Explanations

    hyphenated prefix or suffix

    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
    sth
    -0.07
    dm
    -0.06
     Wunder
    -0.06
    翼
    -0.06
    uple
    -0.06
     stir
    -0.06
     I
    -0.05
     hypert
    -0.05
    Hur
    -0.05
     lâng
    -0.05
    POSITIVE LOGITS
    èİ«åıĬ
    0.09
    æĪijä¸Ģå®ļä¼ļ
    0.08
    .stringify
    0.08
    icismo
    0.08
    amat
    0.08
    åıĸèĢĮ代ä¹ĭ
    0.08
    ãm
    0.08
     Purtroppo
    0.08
    çĭĻåĩ»
    0.08
    ì¹
    0.08
    Activations Density 0.002%

    No Known Activations