© 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. 19715
    Prev
    Next
    INDEX
    Explanations

    alphanumeric identifiers

    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
    otá
    -0.07
    ãģľ
    -0.07
    าà¸Ļุ
    -0.07
    _IRQ
    -0.07
    /welcome
    -0.07
    ÑĢÑį
    -0.07
    çİ°åľºç¡®è®¤
    -0.07
     Continent
    -0.07
    cka
    -0.07
     suffici
    -0.07
    POSITIVE LOGITS
     ê³Ħ
    0.06
    å®ĥå°Ĩ
    0.06
     great
    0.06
    éĩijæĸ¯
    0.06
    çĿ£å¯Ł
    0.06
    御
    0.06
    à¸Ĥ
    0.06
    ustra
    0.06
    adeira
    0.06
    建
    0.06
    Activations Density 0.039%

    No Known Activations