© 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. 22545
    Prev
    Next
    INDEX
    Explanations

    project

    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
     каÑĩ
    -0.05
    ded
    -0.05
    าà¸Ļัà¹īà¸Ļ
    -0.05
    links
    -0.05
    äºĨä¸ĢæĬĬ
    -0.05
    achsen
    -0.05
    ound
    -0.05
     tersebut
    -0.05
     rend
    -0.05
    并éĩĩåıĸ
    -0.05
    POSITIVE LOGITS
     Insgesamt
    0.06
     cale
    0.06
    æ´ĭ
    0.06
    ikle
    0.06
    Fld
    0.06
    زÙħ
    0.06
    isir
    0.06
    EMON
    0.05
    irket
    0.05
    alos
    0.05
    Activations Density 0.112%

    No Known Activations