© 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. 62638
    Prev
    Next
    INDEX
    Explanations

    mathematical formula delimiters

    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
    emento
    -0.08
    ();)
    -0.08
    丸åŃIJ
    -0.08
    åįĥ
    -0.07
    å¦ĤæŀľéľĢè¦ģ
    -0.07
    ernt
    -0.07
    oom
    -0.07
    epen
    -0.07
    /re
    -0.07
    /]
    -0.06
    POSITIVE LOGITS
    adder
    0.08
    -addon
    0.07
    Ø´ÙĬØ©
    0.07
    ucch
    0.07
    .readValue
    0.07
     Fab
    0.06
    ordin
    0.06
    بط
    0.06
     FAB
    0.06
    éĪ
    0.06
    Activations Density 0.005%

    No Known Activations