© 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. 20318
    Prev
    Next
    INDEX
    Explanations

    Kubernetes associated terms

    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
    ergestellt
    -0.07
    rit
    -0.06
    Äŀ
    -0.06
    inger
    -0.06
    бак
    -0.06
    sett
    -0.06
    imenta
    -0.06
    åħ¼ãģŃ
    -0.06
    л
    -0.06
    ernel
    -0.06
    POSITIVE LOGITS
    iose
    0.06
    eka
    0.05
    çݺ
    0.05
    iotic
    0.05
    east
    0.05
    á»Ļi
    0.05
    each
    0.05
    ä¼¼éĶ¦
    0.05
    yi
    0.05
    空çļĦ
    0.05
    Activations Density 0.003%

    No Known Activations