© 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. 22374
    Prev
    Next
    INDEX
    Explanations

    hypergraph, graph, division, broadcast, choice

    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
    çĥĤ
    -0.07
    å¯¹æľ¬
    -0.07
     cru
    -0.06
    éĶŃ
    -0.06
     tart
    -0.06
    .asc
    -0.06
    Compile
    -0.06
    ç³ľçĥĤ
    -0.06
    éĵ¶å±ij
    -0.06
     di
    -0.06
    POSITIVE LOGITS
    amenta
    0.09
    oks
    0.08
     capacities
    0.08
    kunde
    0.08
    irão
    0.07
     MaÃŁe
    0.07
     Capacity
    0.07
    æĭĶåĩº
    0.07
    äºijå³°
    0.07
    aban
    0.07
    Activations Density 0.004%

    No Known Activations