© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20326
    Prev
    Next
    INDEX
    Explanations

    css `box` and related properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¯Ķ为
    -0.06
    oleh
    -0.06
    itness
    -0.06
    omed
    -0.06
    ylko
    -0.06
    best
    -0.06
     Best
    -0.05
    æ¯Ķ
    -0.05
    ãģ¿ãģ¤
    -0.05
    aro
    -0.05
    POSITIVE LOGITS
     generously
    0.06
     overst
    0.06
    lan
    0.05
    kamp
    0.05
    rame
    0.05
    æµ·çĩķ
    0.05
    åħĪçĶŁçļĦ
    0.05
    FontSize
    0.05
    缴æݥ影åĵį
    0.05
     r
    0.05
    Activations Density 0.005%

    No Known Activations