© 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. 19829
    Prev
    Next
    INDEX
    Explanations

    network switch

    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
    üste
    -0.07
    责任åĪ¶
    -0.07
    kits
    -0.06
    对å¤ĸè´¸æĺĵ
    -0.06
    该å±Ģ
    -0.06
    athi
    -0.06
    æľīçĶŁ
    -0.06
    çī¹èģĺ
    -0.06
    天å¤ĸ
    -0.06
    elos
    -0.06
    POSITIVE LOGITS
    ç°ĩ
    0.05
    åĪĨå±Ĥ
    0.05
     ais
    0.05
    好æŃ¹
    0.05
    RF
    0.05
    ort
    0.05
     nata
    0.05
     presid
    0.05
    绣
    0.05
    磩éĺµ
    0.05
    Activations Density 0.004%

    No Known Activations