© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19746
    Prev
    Next
    INDEX
    Explanations

    `els`

    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
    ivers
    -0.06
    iro
    -0.06
    ough
    -0.06
    æį¢ä¸Ģ个
    -0.05
    èĤ²
    -0.05
    çªįéŨ
    -0.05
    ior
    -0.05
    ç³»
    -0.05
    arest
    -0.05
    èĢĮè¿Ļç§į
    -0.05
    POSITIVE LOGITS
    olos
    0.06
     rele
    0.06
     Khang
    0.05
    幡
    0.05
    acos
    0.05
     recons
    0.05
    GU
    0.05
    ä¸įæľį
    0.05
    çıĬçıĬ
    0.05
    els
    0.05
    Activations Density 0.023%

    No Known Activations