© 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. 18078
    Prev
    Next
    INDEX
    Explanations

    Doli, World, Leap, Dream, somewhere, Nu

    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
    oken
    -0.07
    ignon
    -0.06
    ueb
    -0.06
    รั
    -0.06
    ashed
    -0.06
    dont
    -0.06
    æĵŀ
    -0.06
    ÙħÙĬÙĦ
    -0.06
    eway
    -0.06
     whereas
    -0.06
    POSITIVE LOGITS
    inp
    0.07
     appunto
    0.06
    resses
    0.06
     báºŃc
    0.06
    å¸ĮæľĽå¯¹å¤§å®¶
    0.06
     berjudul
    0.06
    gies
    0.06
    ÑĢÑĤом
    0.06
    InBackground
    0.06
    ãĤ²ãĥ¼
    0.06
    Activations Density 0.570%

    No Known Activations