© 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. 11984
    Prev
    Next
    INDEX
    Explanations

    independent random 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
    trup
    -0.09
    lish
    -0.08
    θει
    -0.08
    hund
    -0.08
    大马
    -0.08
    .byte
    -0.08
    sang
    -0.07
    меÑĤи
    -0.07
    æľīä½Ļ
    -0.07
    asty
    -0.07
    POSITIVE LOGITS
     random
    0.08
     altogether
    0.07
     randomness
    0.07
    ness
    0.07
    æĭį
    0.06
    çĭ¬ç«ĭæĢ§
    0.06
     assortment
    0.06
    .random
    0.06
     separately
    0.06
     independ
    0.06
    Activations Density 0.005%

    No Known Activations