© 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. 18505
    Prev
    Next
    INDEX
    Explanations

    sleep and rest

    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
    oke
    -0.06
     pedest
    -0.06
    å¼Ħ
    -0.06
    ias
    -0.06
    ael
    -0.06
    terne
    -0.06
    çī¹æ´¾
    -0.06
     continuam
    -0.06
    erias
    -0.05
     ajusta
    -0.05
    POSITIVE LOGITS
    appy
    0.06
    marks
    0.05
     ÙĤ
    0.05
    imia
    0.05
    меÑĢÑĭ
    0.05
    mark
    0.05
     v
    0.05
    меÑģÑĤи
    0.05
    Marks
    0.05
     markings
    0.05
    Activations Density 0.003%

    No Known Activations