© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42450
    Prev
    Next
    INDEX
    Explanations

    requests, timeouts, or special characters

    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
    æļ¦
    -0.07
    .constructor
    -0.07
    eni
    -0.07
    okka
    -0.07
    à¯ģà®ķ
    -0.06
    lev
    -0.06
    etra
    -0.06
     parade
    -0.06
    arra
    -0.06
    çŃī缸åħ³
    -0.06
    POSITIVE LOGITS
     tadi
    0.08
    åĪļæīį
    0.08
    amai
    0.07
     acer
    0.07
    ä¸Ĭè¿°
    0.07
    æijĬ
    0.07
    åīįè¿°
    0.07
    óÅĤ
    0.07
    ama
    0.07
    æ¡ĵ
    0.07
    Activations Density 0.008%

    No Known Activations