© 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. 14867
    Prev
    Next
    INDEX
    Explanations

    optional string or data types

    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
    	statement
    -0.08
    edul
    -0.08
    ilh
    -0.08
    ingk
    -0.08
     getResource
    -0.08
    mán
    -0.08
    ç½ijç«Ļ导èĪª
    -0.08
    ampur
    -0.08
    anzo
    -0.08
    lington
    -0.08
    POSITIVE LOGITS
    âĢ
    0.07
    Âł
    0.07
    -
    0.06
    庵
    0.06
    ...
    0.06
     output
    0.06
    2
    0.06
    ;
    0.06
    âĢ¦
    0.06
    0
    0.06
    Activations Density 0.016%

    No Known Activations