© 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. 12105
    Prev
    Next
    INDEX
    Explanations

    commented by, asked, Please take

    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
    hest
    -0.08
    两æŀģ
    -0.07
    åįģäºĮç«ł
    -0.07
    angled
    -0.07
    èĪ¶
    -0.07
    ekyll
    -0.07
    ìłģìĿ´
    -0.07
    izon
    -0.07
    illon
    -0.07
    åľ°æŃ¥
    -0.07
    POSITIVE LOGITS
    ouve
    0.08
    enom
    0.07
    Guess
    0.07
    VOKE
    0.07
    çľĭæ¸ħ
    0.06
    unsch
    0.06
    éŃĤ
    0.06
    ÑģÑı
    0.06
     famously
    0.06
    목
    0.06
    Activations Density 0.157%

    No Known Activations