© 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. 21856
    Prev
    Next
    INDEX
    Explanations

    fake news

    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
    оди
    -0.05
    пен
    -0.05
    aced
    -0.05
    å®ī
    -0.05
    ays
    -0.05
    åºĶæĮī
    -0.05
     Again
    -0.05
     Rem
    -0.05
     Re
    -0.05
    RS
    -0.05
    POSITIVE LOGITS
    ä¸Ģåİ»
    0.06
     ngo
    0.06
    æĸĩç«łä¸Ń
    0.06
    rug
    0.06
    ÑĢгÑĥ
    0.06
    Úĺ
    0.06
    prio
    0.06
    åıĸèĢĮ代ä¹ĭ
    0.06
    åħ¨æĸĩéĺħ读
    0.05
    è¹Ń
    0.05
    Activations Density 0.043%

    No Known Activations