© 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. 51669
    Prev
    Next
    INDEX
    Explanations

    remove, exit, operation

    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
    fetch
    -0.07
    åĮ
    -0.07
    CLUDING
    -0.07
    iglio
    -0.07
    .fetch
    -0.07
     embr
    -0.07
    entif
    -0.07
    御
    -0.06
    éħİ
    -0.06
    averse
    -0.06
    POSITIVE LOGITS
    ival
    0.08
     balans
    0.08
    åĭĴæĸ¯
    0.07
    åĭĴ
    0.07
     Fors
    0.07
    å·®åĪĨ
    0.07
    èµ·åĽł
    0.07
    ÛĮØ´
    0.07
    (+
    0.07
     Lop
    0.07
    Activations Density 0.004%

    No Known Activations