© 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. 1905
    Prev
    Next
    INDEX
    Explanations

    = assignment

    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
    ons
    -0.06
    带ç»Ļä½ł
    -0.06
    ÙĬرة
    -0.06
    ãĢĢ
    -0.06
    导读
    -0.06
    quita
    -0.06
    orro
    -0.06
    è¿Ķ
    -0.05
    rens
    -0.05
     duro
    -0.05
    POSITIVE LOGITS
    ãģĿãģĨãģ§
    0.10
    upro
    0.08
    âĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģ
    0.08
    ivs
    0.07
    åIJĮä¸Ĭ
    0.07
     sonstige
    0.07
    elm
    0.07
    éĵ®
    0.07
    å§Ĺ
    0.07
    zinho
    0.07
    Activations Density 0.029%

    No Known Activations