© 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. 16492
    Prev
    Next
    INDEX
    Explanations

    key-value pairs: attribute:

    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
    abis
    -0.08
    indelijk
    -0.08
    ç¬ijæĦı
    -0.07
    ä¸ĢæıIJ
    -0.07
    ead
    -0.07
    æĹłå¿ĥ
    -0.07
    åįĩèµ·
    -0.06
    éĿł
    -0.06
    abilit
    -0.06
    óÅĤ
    -0.06
    POSITIVE LOGITS
    åĽ¢åĽ¢
    0.08
    awah
    0.07
     Duration
    0.07
    meister
    0.07
    ä¸Ģ份
    0.07
    å¿ı
    0.06
    mien
    0.06
    ä¸ĥéĩĮ
    0.06
    aturan
    0.06
    mán
    0.06
    Activations Density 0.001%

    No Known Activations