© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26993
    Prev
    Next
    INDEX
    Explanations

    @rem or @echo

    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
    asty
    -0.08
     vong
    -0.07
    åĪĨå¤ĸ
    -0.07
    ÏĩοÏĤ
    -0.07
    dst
    -0.07
    -envelope
    -0.07
    ilas
    -0.07
    elaar
    -0.07
    صرة
    -0.07
    hen
    -0.06
    POSITIVE LOGITS
    ãģ¾ãģļ
    0.06
    åħĪæĬĬ
    0.06
    isses
    0.06
    BufferData
    0.06
     cla
    0.06
    åIJĥä¸ĢäºĽ
    0.06
    clare
    0.06
    RAY
    0.06
    çĶ¨å¿ĥåİ»
    0.06
    æľīä¸īç§į
    0.06
    Activations Density 0.288%

    No Known Activations