© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42625
    Prev
    Next
    INDEX
    Explanations

    fuel cell

    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
     sortable
    -0.08
    /ajax
    -0.07
    交å¾ħ
    -0.07
    pps
    -0.07
     ray
    -0.07
    æĭįäºĨ
    -0.07
     tal
    -0.07
     Cia
    -0.07
    ïs
    -0.07
    交代
    -0.07
    POSITIVE LOGITS
    çĩĥæĸĻçĶµæ±ł
    0.11
    Harness
    0.09
    fuel
    0.09
     fuel
    0.08
    çĩĥæĸĻ
    0.08
     electrodes
    0.08
     Fuel
    0.08
    çĶµæŀģ
    0.08
    Fuel
    0.08
    spark
    0.08
    Activations Density 0.046%

    No Known Activations