© 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. 26335
    Prev
    Next
    INDEX
    Explanations

    fire and ignition

    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
    uken
    -0.07
    èĭ¦çĵľ
    -0.07
    ilar
    -0.07
    水产åĵģ
    -0.07
    reno
    -0.07
    沧海
    -0.07
    èĢIJåİĭ
    -0.07
    plib
    -0.07
     Slam
    -0.07
    zwi
    -0.07
    POSITIVE LOGITS
    æĺİçģ«
    0.15
    çĩĥçĥ§
    0.14
    çĨĦçģŃ
    0.14
    çĩĥçĥ§çļĦ
    0.13
     burning
    0.13
     ignition
    0.13
    çĨĬçĨĬ
    0.13
     ignited
    0.13
     combustion
    0.13
    çģ«çĦ°
    0.13
    Activations Density 0.102%

    No Known Activations