© 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. 57062
    Prev
    Next
    INDEX
    Explanations

    cyan, magenta, yellow

    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
    à¹ģà¸ģ
    -0.06
    .nasa
    -0.06
    .spatial
    -0.06
    åIJł
    -0.06
    çĤ¹äº®
    -0.06
    平衡
    -0.06
     fix
    -0.06
     ÙħÙĩ
    -0.06
    çݯå¢ĥè´¨éĩı
    -0.06
     compass
    -0.06
    POSITIVE LOGITS
    鸥
    0.09
    adal
    0.08
    çĮªèĤĿ
    0.08
    åħĭåħ°
    0.07
    ussa
    0.07
    onnal
    0.07
    è½īæıĽ
    0.07
    ToDevice
    0.07
    matic
    0.07
    druck
    0.07
    Activations Density 0.002%

    No Known Activations