© 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. 26448
    Prev
    Next
    INDEX
    Explanations

    incomplete combustion or burning

    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
    mut
    -0.07
    åģļäºĭæĥħ
    -0.07
     اÙĦرا
    -0.07
     Bakan
    -0.07
     relo
    -0.07
    ðŁĻĤ
    -0.07
     lore
    -0.07
    fiz
    -0.07
    |R
    -0.07
    _Filter
    -0.07
    POSITIVE LOGITS
    çĩĥçĥ§
    0.12
     combustion
    0.11
    çĦļçĥ§
    0.10
    à¹Ģà¸ľà¸²
    0.10
    碳
    0.10
    çĩĥçĥ§çļĦ
    0.10
     carbon
    0.09
     burning
    0.09
    æ°§
    0.09
     burned
    0.08
    Activations Density 0.008%

    No Known Activations