© 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. 19540
    Prev
    Next
    INDEX
    Explanations

    ruins and remains of historical sites

    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
    idi
    -0.06
     Europeo
    -0.06
     unusual
    -0.06
    dued
    -0.05
    oli
    -0.05
     rare
    -0.05
    ffen
    -0.05
    olson
    -0.05
    èĢģæŧ
    -0.05
    asis
    -0.05
    POSITIVE LOGITS
     mues
    0.06
     Freed
    0.05
    lesh
    0.05
    ìľ
    0.05
    باØŃ
    0.05
    åĽ½éĻħä¼ļå±ķä¸Ńå¿ĥ
    0.05
     buzzing
    0.05
    wes
    0.05
     spect
    0.05
     explan
    0.05
    Activations Density 0.013%

    No Known Activations