© 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. 46430
    Prev
    Next
    INDEX
    Explanations

    breeding program conducted

    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
    åIJijæĹ¥
    -0.08
    ä¸Ģ级
    -0.08
    æŃ£åIJij
    -0.07
    çĻ¾åĢį
    -0.07
    usc
    -0.07
    infeld
    -0.07
    ward
    -0.07
    az
    -0.07
    纪念é¦Ĩ
    -0.07
    ä¿±è¿Ľ
    -0.07
    POSITIVE LOGITS
    rips
    0.07
    pil
    0.07
    æĭĨå¼Ģ
    0.07
    rape
    0.07
    åIJĦåľ°åĮº
    0.06
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    0.06
    DataStream
    0.06
    .old
    0.06
    oir
    0.06
    abra
    0.06
    Activations Density 0.003%

    No Known Activations