© 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. 22080
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
     bund
    -0.07
    bund
    -0.07
    æī«çłģåħ³æ³¨
    -0.07
    çľ¼è§ģ
    -0.06
    opping
    -0.06
    æĤī
    -0.06
    elsen
    -0.06
     convient
    -0.06
     io
    -0.06
    ä»ĵ
    -0.06
    POSITIVE LOGITS
    TPL
    0.08
    大åı¯
    0.08
    éľĸ
    0.08
     Maggio
    0.07
    rive
    0.07
     zaraz
    0.07
    IRM
    0.07
    åħ¬åı¸çŃī
    0.07
    ä»Ģä¹Īåij¢
    0.07
    èľľæľĪ
    0.07
    Activations Density 0.003%

    No Known Activations