© 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. 46868
    Prev
    Next
    INDEX
    Explanations

    exhaust gas

    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
    staat
    -0.07
    æĬĹæű
    -0.07
     ge
    -0.06
    kau
    -0.06
    मित
    -0.06
    .Mutex
    -0.06
    تز
    -0.06
    PLIC
    -0.06
    ä¸Ĭä¸ĭçıŃ
    -0.06
    ĵĺ
    -0.06
    POSITIVE LOGITS
    ä½ĻçĥŃ
    0.11
    å°¾æ°Ķ
    0.10
    æİĴæĶ¾
    0.10
     gases
    0.10
    çĥŁæ°Ķ
    0.10
     emission
    0.10
     emissions
    0.09
    åįĩåħ¥
    0.09
    otto
    0.09
    (exit
    0.09
    Activations Density 0.018%

    No Known Activations