© 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. 29668
    Prev
    Next
    INDEX
    Explanations

    fast processing or shipping

    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
    zelf
    -0.10
    alto
    -0.09
    åĭĥåĭĥ
    -0.09
    halb
    -0.09
    ÙĬÙĬÙĨ
    -0.09
    icoli
    -0.09
    并èĮĤ
    -0.09
     forfait
    -0.09
    OutOfBounds
    -0.09
    OutOfRangeException
    -0.09
    POSITIVE LOGITS
    ened
    0.14
    idious
    0.13
    ening
    0.12
    -paced
    0.10
     chóng
    0.09
    eners
    0.08
    /fast
    0.08
     enough
    0.08
    (er
    0.08
    å¿«çļĦ
    0.08
    Activations Density 0.058%

    No Known Activations