© 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. 9242
    Prev
    Next
    INDEX
    Explanations

    foreign language or specific terms

    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
    æIJŃä¸Ĭ
    -0.07
    ,msg
    -0.07
     ném
    -0.07
    žel
    -0.07
    ansa
    -0.07
    èĬĿ
    -0.06
    Far
    -0.06
    çļĦ社ä¼ļ
    -0.06
    éĢģ
    -0.06
    ham
    -0.06
    POSITIVE LOGITS
    parg
    0.07
    nad
    0.07
    림
    0.07
    utti
    0.07
    绣æĭĽ
    0.06
    è§ģçļĦ
    0.06
    nios
    0.06
    è§ģ
    0.06
     clar
    0.06
    èĤ²æīį
    0.06
    Activations Density 0.063%

    No Known Activations