© 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. 60307
    Prev
    Next
    INDEX
    Explanations

    special characters or invalid encoding

    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
    ness
    -0.10
    ation
    -0.10
    ier
    -0.09
    ERIA
    -0.08
    gregate
    -0.08
    ighbors
    -0.08
    иÑħ
    -0.08
    èĢIJåĬ³
    -0.08
    vironment
    -0.08
    ular
    -0.08
    POSITIVE LOGITS
    Ŀ
    0.10
    Ĩ
    0.10
    zelfde
    0.09
    åĴĮ
    0.08
    ly
    0.08
    ï¸İ
    0.08
    ecter
    0.08
    Ĵ
    0.07
     ngo
    0.07
    ë¡ľ
    0.07
    Activations Density 0.003%

    No Known Activations