© 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. 21883
    Prev
    Next
    INDEX
    Explanations

    numbers and names

    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
    åģĩ
    -0.06
    lector
    -0.06
    False
    -0.06
    hir
    -0.06
    à¸ķระ
    -0.05
    åĽłä¸ºåıªæľī
    -0.05
    æİ¨è¿Ľä¼ļ
    -0.05
    acle
    -0.05
    dad
    -0.05
    pok
    -0.05
    POSITIVE LOGITS
    åŃļ
    0.07
    ä¸Ģè¨Ģ
    0.05
    åĩºçĤī
    0.05
    UBE
    0.05
     uncomp
    0.05
    szer
    0.05
    AIL
    0.05
     Zug
    0.05
    ensioni
    0.05
     coupled
    0.05
    Activations Density 0.055%

    No Known Activations