© 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. 15422
    Prev
    Next
    INDEX
    Explanations

    -ius, -y, -ox

    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
    аÑĤа
    -0.09
    atable
    -0.09
    aters
    -0.08
    atab
    -0.08
    Ùİد
    -0.08
    atern
    -0.08
    ạc
    -0.08
    à¸Ķม
    -0.08
    à½Ħ
    -0.08
    adow
    -0.08
    POSITIVE LOGITS
    åŃIJçļĦ
    0.14
    ies
    0.14
    ius
    0.14
    ÛĮ
    0.14
    iness
    0.14
    ×Ļ×ķת
    0.13
    ie
    0.13
    иÑİ
    0.13
    inya
    0.13
    ious
    0.13
    Activations Density 3.387%

    No Known Activations