© 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. 62538
    Prev
    Next
    INDEX
    Explanations

    i-to-any

    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
    añ
    -0.06
    è¡Į驶çļĦ
    -0.06
    交åĪ°
    -0.06
    ä½łè¯´çļĦ
    -0.06
    æĢĢä¸Ń
    -0.06
    vest
    -0.06
    kia
    -0.06
     contradictory
    -0.06
    imson
    -0.06
    .Compose
    -0.06
    POSITIVE LOGITS
    æĺĬ天
    0.08
    usse
    0.08
    转移
    0.08
     outgoing
    0.08
    ợn
    0.08
     اÙĨتÙĤاÙĦ
    0.08
    æĦıæĥ³
    0.08
    umpt
    0.08
    -pane
    0.08
     lej
    0.08
    Activations Density 0.005%

    No Known Activations