© 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. 41114
    Prev
    Next
    INDEX
    Explanations

    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
    çħ§é¡¾
    -0.08
    cret
    -0.08
    //'
    -0.07
    å¿ĥçĹħ
    -0.07
    éĤ£äºĽ
    -0.07
    åij¨ä¸Ģèĩ³
    -0.07
    /rfc
    -0.07
    oday
    -0.07
    çIJĨæīĢ
    -0.07
    amba
    -0.07
    POSITIVE LOGITS
    çĩĥçĥ§
    0.09
    çĿĢçģ«
    0.08
     combustion
    0.07
     burning
    0.07
    çģŃçģ«
    0.07
    çģ«çĦ°
    0.07
    éļĶçĿĢ
    0.07
    åı¯çĩĥ
    0.07
    çĩĥæĶ¾
    0.07
    animation
    0.07
    Activations Density 0.002%

    No Known Activations