© 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. 20001
    Prev
    Next
    INDEX
    Explanations

    Mediterranean spur

    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
    elow
    -0.06
     realis
    -0.06
     побÑĭ
    -0.06
    é¢ĦéĢī
    -0.06
     kerto
    -0.06
    è§£è°ľ
    -0.06
     pang
    -0.06
    ç³ľ
    -0.06
    èĥ½åĬĽåıĬ
    -0.06
     seiz
    -0.06
    POSITIVE LOGITS
    0.06
    å¼ı
    0.06
    çķĻ
    0.05
    çķ¥
    0.05
    åľ°è¡¨
    0.05
    çĶ¨
    0.05
    沸
    0.05
     st
    0.05
    .gov
    0.05
    å¼ı设计
    0.05
    Activations Density 0.049%

    No Known Activations