© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19720
    Prev
    Next
    INDEX
    Explanations

    oding California essay

    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
    anye
    -0.07
    ضة
    -0.07
    ucin
    -0.06
    ئÙħ
    -0.06
    endien
    -0.06
    –and
    -0.06
    hme
    -0.06
     láp
    -0.06
     dura
    -0.06
    ewe
    -0.06
    POSITIVE LOGITS
     vern
    0.05
    r
    0.05
     pro
    0.05
    iv
    0.05
     blo
    0.05
    d
    0.05
    l
    0.05
     etc
    0.05
    é¢ĺ
    0.05
     Monkey
    0.05
    Activations Density 0.013%

    No Known Activations