© 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. 48357
    Prev
    Next
    INDEX
    Explanations

    space and memory usage

    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
    illi
    -0.08
    uada
    -0.08
    sbin
    -0.08
    utow
    -0.07
    -submit
    -0.07
    engg
    -0.07
    eries
    -0.07
    ecin
    -0.07
    æĹ¥çĶŁ
    -0.07
    äºĨä¸Ģéģį
    -0.07
    POSITIVE LOGITS
     usage
    0.08
    空éĹ´
    0.07
     storage
    0.07
     storing
    0.07
     ê³µê°Ħ
    0.07
    space
    0.06
    åĴĮ使çĶ¨
    0.06
     memory
    0.06
     space
    0.06
    antz
    0.06
    Activations Density 0.011%

    No Known Activations