© 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. 24301
    Prev
    Next
    INDEX
    Explanations

    railway lines and stations

    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¸įæħİ
    -0.07
    åĶī
    -0.06
    onese
    -0.06
    é½IJ
    -0.06
    éļı
    -0.06
    æĥij
    -0.06
    æļĩ
    -0.06
    åķ
    -0.06
    Ùħج
    -0.06
    éĩĩ
    -0.06
    POSITIVE LOGITS
    éĢĶä¸Ń
    0.11
    缮çļĦåľ°
    0.11
     destinations
    0.11
     route
    0.10
    ä¸ŃéĢĶ
    0.10
    æĽ´è¿ľ
    0.10
    éĢĶç»ı
    0.10
     vÃŃa
    0.10
     destination
    0.10
    route
    0.09
    Activations Density 0.229%

    No Known Activations