© 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. 38206
    Prev
    Next
    INDEX
    Explanations

    basis, coordinates, frames, reference

    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
    è¿Ļéĥ¨åĪĨ
    -0.08
     Compon
    -0.08
    toral
    -0.08
    inel
    -0.07
     ÑģоÑĨиалÑĮного
    -0.07
    çİ¯å²Ľ
    -0.07
     Rimini
    -0.07
    educt
    -0.07
    ä½ľä¸ºä¸Ģ个
    -0.07
    ecten
    -0.07
    POSITIVE LOGITS
    orth
    0.08
    thon
    0.07
    èŃī
    0.07
    zs
    0.07
     Orth
    0.07
     chosen
    0.07
     coordinates
    0.07
    èĪĴæľį
    0.07
    æĸ¹ä¾¿
    0.06
    .local
    0.06
    Activations Density 0.018%

    No Known Activations