© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 40922
    Prev
    Next
    INDEX
    Explanations

    integral expression or command line

    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
    (prediction
    -0.06
    _SWAP
    -0.06
    дзе
    -0.06
    第ä¸Ģä»¶äºĭ
    -0.06
    åĽĽåŃĹ
    -0.06
    åĪĩ
    -0.06
     predictable
    -0.06
    urin
    -0.06
    ä¿Ŀé¤Ĭ
    -0.06
    ãĥĥãĤ«ãĥ¼
    -0.06
    POSITIVE LOGITS
    erias
    0.10
    nder
    0.08
    ocken
    0.08
    /ge
    0.07
    rust
    0.07
    æļ¢
    0.07
    InputStream
    0.07
    rou
    0.07
    chest
    0.07
    _histogram
    0.07
    Activations Density 0.003%

    No Known Activations