© 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. 41821
    Prev
    Next
    INDEX
    Explanations

    transformations and ways to define criteria

    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
    ecker
    -0.09
     litt
    -0.08
     Consolid
    -0.08
    assis
    -0.08
     résol
    -0.08
    å¿ħçľĭ
    -0.07
    æķ¬ä¸ļ
    -0.07
    upert
    -0.07
    æij¸æ¸ħ
    -0.07
    atori
    -0.07
    POSITIVE LOGITS
     inspired
    0.10
     functions
    0.09
     designed
    0.09
     incorporating
    0.08
    Functions
    0.08
    修饰
    0.08
     Inspired
    0.08
     expression
    0.07
     Functions
    0.07
     derivatives
    0.07
    Activations Density 0.045%

    No Known Activations