© 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. 4362
    Prev
    Next
    INDEX
    Explanations

    time formats

    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
    ORN
    -0.08
    ége
    -0.08
    大家æĹı
    -0.08
    zeh
    -0.08
    åħ¹
    -0.08
    ÑĢио
    -0.08
    üle
    -0.08
    åİĭæľº
    -0.08
    ULE
    -0.07
    BlockSize
    -0.07
    POSITIVE LOGITS
    evin
    0.06
    ترÛĮ
    0.06
     Uhr
    0.06
    人影
    0.06
    оÑĤа
    0.06
    æ±ĩéĽĨäºĨ
    0.06
    explained
    0.06
    ¹
    0.06
    ä¹ĭéĻħ
    0.06
    ä¸Ģä½ľ
    0.06
    Activations Density 0.061%

    No Known Activations