© 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. 65494
    Prev
    Next
    INDEX
    Explanations

    greek letters and math symbols

    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
    ÙĬر
    -0.07
    "T
    -0.07
    urv
    -0.07
    azan
    -0.06
    gle
    -0.06
    urz
    -0.06
    upe
    -0.06
     Gib
    -0.06
    anaf
    -0.06
    çľ¼èĬ±
    -0.06
    POSITIVE LOGITS
    ¿
    0.08
    änge
    0.07
     fucks
    0.07
    eman
    0.07
    eschi
    0.07
    ¾
    0.07
    itzer
    0.07
    ÄįiÄĩ
    0.07
    ëģĶ
    0.07
    inker
    0.07
    Activations Density 0.098%

    No Known Activations