© 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. 17906
    Prev
    Next
    INDEX
    Explanations

    lead and mercury

    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
    éĻIJåĪ¶æĢ§
    -0.06
    å¾Ī强çļĦ
    -0.05
    è®Ń
    -0.05
    ä¸į容æĺĵ
    -0.05
    强度é«ĺ
    -0.05
     radical
    -0.05
    ope
    -0.05
    رÙĬØŃ
    -0.05
     tougher
    -0.05
    ulier
    -0.05
    POSITIVE LOGITS
    å®īä¹IJ
    0.07
    éĵħ
    0.06
    à¸ļาà¸Ĺ
    0.06
    iegel
    0.06
     mercury
    0.06
     Kül
    0.06
     Soros
    0.06
    anut
    0.06
     Venda
    0.06
     Klos
    0.06
    Activations Density 0.029%

    No Known Activations