© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22564
    Prev
    Next
    INDEX
    Explanations

    version number or list count

    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
    Negative Logits
    è¯ķè¯ķ
    -0.06
     plate
    -0.05
    kd
    -0.05
    ä¸Ĭåı°
    -0.05
    è¯ķè¿IJè¡Į
    -0.05
    aka
    -0.05
     HR
    -0.05
    åĭĥ
    -0.05
    elder
    -0.05
    kb
    -0.05
    POSITIVE LOGITS
    fur
    0.06
    èıģ
    0.06
     Soweit
    0.06
    æĨ¬
    0.06
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    0.06
     Wegen
    0.06
    atot
    0.06
    jen
    0.06
    fare
    0.06
    èį¤
    0.06
    Activations Density 0.001%

    No Known Activations