© 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. 12608
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or numbers

    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
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.09
    ä¸Ģæī«
    -0.08
    ieties
    -0.08
    ianas
    -0.08
    vaard
    -0.08
    vertiser
    -0.08
    à¸ŀีà¹Īà¸Ļà¹īà¸Ńà¸ĩ
    -0.08
    æĭ³
    -0.08
    ableObject
    -0.07
    รà¹īาย
    -0.07
    POSITIVE LOGITS
    acam
    0.08
     Mod
    0.07
    Mod
    0.06
    ÏĢÎŃ
    0.06
     mod
    0.06
    é¼İ
    0.06
    pe
    0.06
     Gio
    0.06
    PE
    0.06
    _verbose
    0.05
    Activations Density 0.013%

    No Known Activations