© 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. 17070
    Prev
    Next
    INDEX
    Explanations

    Minister Corruption Railroad building Brigade gene

    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
    ınca
    -0.06
    endar
    -0.06
    caras
    -0.06
     consigliato
    -0.06
    enger
    -0.06
    acar
    -0.06
     **:**
    -0.06
    agar
    -0.06
    ÑĩиÑĤ
    -0.06
    alker
    -0.06
    POSITIVE LOGITS
    æłĩ
    0.06
     fat
    0.06
     div
    0.05
     asc
    0.05
     dev
    0.05
    -\
    0.05
     def
    0.05
    irsch
    0.05
    ç¥ŀ
    0.05
    éĩī
    0.05
    Activations Density 0.006%

    No Known Activations