© 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. 23103
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and programming constructs

    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
    apore
    -0.08
    ARGE
    -0.08
    åĪ·åĪ·
    -0.07
    天宫
    -0.07
    ç²ķ
    -0.07
    æ¸ħæ´ģåį«çĶŁ
    -0.07
    ä¹Łä¸įæĢķ
    -0.07
    .loadData
    -0.07
    isman
    -0.07
    fade
    -0.07
    POSITIVE LOGITS
    硬
    0.08
     вне
    0.07
    رÙĪس
    0.07
     separately
    0.07
    zza
    0.07
    è¶ħ
    0.07
    æĪIJçĨŁ
    0.07
    å¢ĥå¤ĸ
    0.06
    èī³
    0.06
    abas
    0.06
    Activations Density 0.105%

    No Known Activations