© 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. 19943
    Prev
    Next
    INDEX
    Explanations

    future scenarios and predictions

    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
     theoretical
    -0.06
    dech
    -0.05
    arge
    -0.05
     undert
    -0.05
     momento
    -0.05
    phan
    -0.05
    çļĦçIJĨ论
    -0.05
    ridge
    -0.05
    éļıæŶ
    -0.05
     frustrated
    -0.05
    POSITIVE LOGITS
    ÏĢί
    0.06
     agré
    0.06
    unk
    0.06
    ÑĥÑĢ
    0.06
     اعÙħاÙĦ
    0.06
    ëŁ
    0.06
    åĦ¿å¥³
    0.05
    å¼ķ导åŃ©åŃIJ
    0.05
     HomeComponent
    0.05
    ówczas
    0.05
    Activations Density 0.008%

    No Known Activations