© 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. 57405
    Prev
    Next
    INDEX
    Explanations

    variable and function definitions

    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
    اÙģت
    -0.08
    анÑĤа
    -0.07
    åŁºéĩijçļĦ
    -0.07
     СоÑĤ
    -0.07
    uves
    -0.07
    onger
    -0.07
     Karr
    -0.07
    çĽĪçĽĪ
    -0.07
    cript
    -0.07
    ä¹°çĤ¹
    -0.07
    POSITIVE LOGITS
    orio
    0.07
    ory
    0.07
    并å°Ĩåħ¶
    0.07
    æĽ¿æį¢
    0.07
    裹
    0.07
    itur
    0.07
    xe
    0.06
    aseline
    0.06
    urai
    0.06
     replaces
    0.06
    Activations Density 0.157%

    No Known Activations