© 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. 10120
    Prev
    Next
    INDEX
    Explanations

    stars, rocket, numbers, code-like 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
    åĽº
    -0.08
     lc
    -0.07
    ugg
    -0.07
    æľīæĿ¡
    -0.07
    åIJįåī¯åħ¶å®ŀçļĦ
    -0.07
    alker
    -0.07
    ensiva
    -0.07
    orius
    -0.07
    æĬľãģį
    -0.07
    Pros
    -0.07
    POSITIVE LOGITS
    _BOTH
    0.08
    bogen
    0.07
    å©ķ
    0.07
    irti
    0.07
    ÙĪا
    0.07
    asang
    0.06
    æĪİ
    0.06
    å½¼
    0.06
    _bid
    0.06
    agers
    0.06
    Activations Density 0.247%

    No Known Activations