© 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. 38703
    Prev
    Next
    INDEX
    Explanations

    names and roles

    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
    æīİå®ŀçļĦ
    -0.07
    å¦Ĥä¸Ģ
    -0.07
    figcaption
    -0.07
     Secrets
    -0.07
    uket
    -0.07
    embers
    -0.06
    nev
    -0.06
    ��
    -0.06
    frist
    -0.06
    å¼łå¿Ĺ
    -0.06
    POSITIVE LOGITS
    pth
    0.07
    uters
    0.07
    interp
    0.07
    å¼ķéĩı
    0.07
    -tool
    0.07
     zugleich
    0.07
    inder
    0.07
    iscard
    0.06
    çĥĻåį°
    0.06
    dom
    0.06
    Activations Density 0.016%

    No Known Activations