© 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. 42188
    Prev
    Next
    INDEX
    Explanations

    optional type indicators

    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
    缸è·Ŀ
    -0.08
    ׾×Ķ
    -0.07
    ioc
    -0.07
     Colombo
    -0.06
    ||||
    -0.06
    tang
    -0.06
    æĽ¼è°·
    -0.06
    åĪĨæķ£
    -0.06
    locator
    -0.06
    enant
    -0.06
    POSITIVE LOGITS
    çĴĢ
    0.07
    _INTEGER
    0.07
     integers
    0.07
    åĨįæ·»
    0.07
    çĨł
    0.07
    é¡¿äºĨ
    0.07
    家ä¸ŃçļĦ
    0.07
    _PIPE
    0.06
     Constructors
    0.06
     âĦķ
    0.06
    Activations Density 0.001%

    No Known Activations