© 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. 20811
    Prev
    Next
    INDEX
    Explanations

    recently reported that

    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
     speech
    -0.05
    onn
    -0.05
    rag
    -0.05
    æ±Ĥ解
    -0.05
    way
    -0.05
    eval
    -0.05
    èµĦæºIJ
    -0.05
    ag
    -0.05
    _resources
    -0.04
     Speech
    -0.04
    POSITIVE LOGITS
    çĶŁçī©åѦ
    0.07
    multiline
    0.07
     molecular
    0.06
     Следова
    0.06
    éĢı亮
    0.06
    ä¸Ŀ
    0.06
     implicated
    0.06
     Molecular
    0.06
    nitz
    0.06
     unrecognized
    0.06
    Activations Density 3.210%

    No Known Activations