© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17915
    Prev
    Next
    INDEX
    Explanations

    DNA/RNA samples or biological samples

    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
     Sim
    -0.07
    Sim
    -0.07
     sim
    -0.06
    模æĭŁ
    -0.06
    模仿
    -0.06
    æŁ¥çľĭ详æĥħ
    -0.06
     simulation
    -0.06
     simulate
    -0.06
     Simulation
    -0.06
    ä»¿çľŁ
    -0.06
    POSITIVE LOGITS
     samples
    0.06
    æīİ
    0.06
    åİ»ä½ķ
    0.06
    _samples
    0.06
    åıĸæł·
    0.06
    samples
    0.06
     Samples
    0.06
    itters
    0.05
     containing
    0.05
     securely
    0.05
    Activations Density 0.626%

    No Known Activations