© 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. 33258
    Prev
    Next
    INDEX
    Explanations

    multi-dimensional arrays and lists

    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
    åijĬ
    -0.07
     bare
    -0.07
    hel
    -0.06
     Bare
    -0.06
    åĬ©
    -0.06
    æĺ¯éĿŀ
    -0.06
    åįĬçĤ¹
    -0.06
    çĻ½éª¨
    -0.06
    ambi
    -0.06
    人身
    -0.06
    POSITIVE LOGITS
     parch
    0.08
    è¦ģæ±ĤåIJĦ
    0.08
     каждаÑı
    0.08
     à¹ģà¸ķà¹Īละ
    0.08
    collection
    0.08
    _collection
    0.08
    åµĮå¥Ĺ
    0.08
     flattened
    0.08
     cỡ
    0.08
    èĤ¢
    0.08
    Activations Density 0.101%

    No Known Activations