© 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. 56275
    Prev
    Next
    INDEX
    Explanations

    'albanés', 'inline-four', 'keyboard', 'DNA', 'females', 'vocals'

    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
    ä¸įåı¯èĥ½çļĦ
    -0.07
    åŃĺåľ¨ä¸Ģå®ļçļĦ
    -0.07
    åħ·æľīä¸Ģå®ļçļĦ
    -0.07
    æĥħæĢĢ
    -0.07
    eer
    -0.07
    çĶ·çļĦ
    -0.07
    èĤ¡æĿĥè´¨æĬ¼
    -0.07
    .exc
    -0.07
    äºİä¸Ģ
    -0.07
    EEP
    -0.07
    POSITIVE LOGITS
     **.**
    0.07
     Wach
    0.07
    ovy
    0.06
    دÙĨ
    0.06
    awns
    0.06
     mainland
    0.06
    etails
    0.06
    itr
    0.06
    èıľ
    0.06
    èĢ
    0.06
    Activations Density 0.062%

    No Known Activations