© 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. 19738
    Prev
    Next
    INDEX
    Explanations

    programming output commands

    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
    ât
    -0.06
    bridge
    -0.06
    åıĹæĥł
    -0.06
    peÄį
    -0.06
    eras
    -0.06
    ÏĦÏī
    -0.06
    onde
    -0.05
    EqualTo
    -0.05
    é²ľèĤī
    -0.05
    åİŁçŁ³
    -0.05
    POSITIVE LOGITS
    li
    0.05
    mob
    0.05
    æĹĭ
    0.05
    erving
    0.05
    _li
    0.05
    åıĮè¾¹
    0.05
    erved
    0.05
    æŶ令
    0.05
    gen
    0.05
    erves
    0.05
    Activations Density 0.046%

    No Known Activations