© 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. 42449
    Prev
    Next
    INDEX
    Explanations

    code structure elements

    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
    å¤ĩ
    -0.08
    åİ»ä½ķ
    -0.08
    ire
    -0.07
    opro
    -0.07
    utura
    -0.07
     Lane
    -0.07
    åħ´å¥ĭ
    -0.06
    rego
    -0.06
    ivet
    -0.06
     trắc
    -0.06
    POSITIVE LOGITS
    åij¦
    0.08
    :red
    0.07
    åĪĨåī²
    0.07
    NUM
    0.07
    afb
    0.07
    zinho
    0.07
    ergarten
    0.07
    éķĸ
    0.07
    çľĭçĤ¹
    0.06
    ândia
    0.06
    Activations Density 0.003%

    No Known Activations