© 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. 1733
    Prev
    Next
    INDEX
    Explanations

    Riemannian metric tensor

    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
    esen
    -0.07
    нде
    -0.07
     coro
    -0.07
     Coro
    -0.07
    igd
    -0.07
     interle
    -0.07
    estal
    -0.07
     pross
    -0.07
    gnu
    -0.07
    trand
    -0.06
    POSITIVE LOGITS
     tensor
    0.08
    Tensor
    0.08
    tensor
    0.08
     tensors
    0.08
    .tight
    0.08
     contraction
    0.07
    emer
    0.07
     dij
    0.07
     Tensor
    0.07
    ähler
    0.07
    Activations Density 0.005%

    No Known Activations