© 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. 20299
    Prev
    Next
    INDEX
    Explanations

    android xml attributes

    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
    itude
    -0.07
     thereof
    -0.06
    abeth
    -0.06
    ation
    -0.06
    ileged
    -0.06
    ure
    -0.06
    olia
    -0.06
    éĽĦåİļçļĦ
    -0.06
    less
    -0.06
    ness
    -0.06
    POSITIVE LOGITS
     referenced
    0.06
    çĶŁçļĦ
    0.06
    upe
    0.06
     tá»ĩ
    0.05
    enam
    0.05
    宿
    0.05
    raca
    0.05
     lit
    0.05
    aranya
    0.05
    shiv
    0.05
    Activations Density 0.022%

    No Known Activations