© 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. 20622
    Prev
    Next
    INDEX
    Explanations

    this article

    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
    thon
    -0.06
    innacle
    -0.06
    terra
    -0.06
    uthor
    -0.06
    vers
    -0.06
    äºĶæĮĩ
    -0.06
    пло
    -0.06
    ignon
    -0.05
    elm
    -0.05
     duplex
    -0.05
    POSITIVE LOGITS
    è±Ĩ
    0.06
    ç´¢
    0.05
    åįĶ
    0.05
    åĬĽå¼º
    0.05
     prevalent
    0.05
    åįĥ
    0.05
     Agreement
    0.05
    å½¢
    0.05
    ofi
    0.05
    æŁ¥
    0.05
    Activations Density 0.002%

    No Known Activations