© 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. 20093
    Prev
    Next
    INDEX
    Explanations

    take in, take to, take risks

    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
     interconnected
    -0.05
    ä»Ĭ天å°ıç¼ĸå°±
    -0.05
    elas
    -0.05
     carc
    -0.05
    éľĸ
    -0.05
    ç²ķ
    -0.05
     infi
    -0.05
     infused
    -0.05
     ag
    -0.05
     inté
    -0.05
    POSITIVE LOGITS
    åIJij被åijĬ
    0.07
    iphy
    0.06
    åĮĸäºĨ
    0.06
    IOD
    0.06
    ihu
    0.06
    RIX
    0.06
    ifax
    0.06
    ãģ³
    0.06
     Disabilities
    0.06
    iserie
    0.06
    Activations Density 0.003%

    No Known Activations