© 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. 28963
    Prev
    Next
    INDEX
    Explanations

    this context usage

    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
    å°±æĺ¯æĪijçļĦ
    -0.08
    ieri
    -0.08
    etable
    -0.07
    SetName
    -0.07
    edelta
    -0.07
    oire
    -0.07
    bons
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    oir
    -0.07
    pics
    -0.07
    POSITIVE LOGITS
    çĶ¨æ³ķ
    0.12
     usage
    0.10
    两å¤Ħ
    0.08
     Usage
    0.08
    使çĶ¨çļĦæĺ¯
    0.08
     context
    0.07
    Context
    0.07
    èĢĥ究
    0.07
    ivere
    0.07
    使çĶ¨æĥħåĨµ
    0.07
    Activations Density 0.018%

    No Known Activations