© 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. 22146
    Prev
    Next
    INDEX
    Explanations

    world as we know it

    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
    woods
    -0.07
    wick
    -0.06
    ä¸įæĭĶ
    -0.06
    igham
    -0.06
    estyle
    -0.06
    èĩªæľīèµĦéĩij
    -0.06
     keman
    -0.06
    åĽ½å®¶æĶ¿çŃĸ
    -0.06
    æĹłçĹķ
    -0.06
     à¸ģัà¸Ļ
    -0.06
    POSITIVE LOGITS
    ung
    0.06
     Ñģло
    0.05
     rev
    0.05
    å°¤åħ¶æĺ¯
    0.05
    UNG
    0.05
    æľīå¿ĥ
    0.05
    第ä¸Ģéĥ¨
    0.05
    èĽ
    0.05
     conglomer
    0.05
     wide
    0.05
    Activations Density 0.027%

    No Known Activations