© 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. 19310
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

    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
    ÃīR
    -0.06
    ocado
    -0.06
    ATUS
    -0.06
    atus
    -0.06
    çħ§
    -0.06
     esaur
    -0.06
    oudre
    -0.06
    çľĭåĪ°è¿Ļ个
    -0.06
      ↵    ↵
    -0.06
    aiss
    -0.06
    POSITIVE LOGITS
    èµ¢
    0.06
    åĪ«
    0.05
    æ·±
    0.05
    ug
    0.05
    æ·¡
    0.05
     Pug
    0.05
    ãĢģ
    0.05
    骨æĬĺ
    0.05
    cole
    0.05
     Scre
    0.05
    Activations Density 0.051%

    No Known Activations