© 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. 46219
    Prev
    Next
    INDEX
    Explanations

    config files or settings

    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
    ÑĤии
    -0.08
    ilog
    -0.07
     ÑĤÑĢо
    -0.07
    客
    -0.07
    红è±Ĩ
    -0.07
    senz
    -0.06
    esign
    -0.06
    agers
    -0.06
    fa
    -0.06
    otted
    -0.06
    POSITIVE LOGITS
     Rauch
    0.08
    ierce
    0.08
    Jackson
    0.07
     impun
    0.07
    ameleon
    0.07
    å©¿
    0.07
     ìŀ¡
    0.07
    orth
    0.07
     localVar
    0.07
    lange
    0.07
    Activations Density 0.003%

    No Known Activations