© 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. 16575
    Prev
    Next
    INDEX
    Explanations

    for use with

    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
    fé
    -0.06
    'n
    -0.06
    è»
    -0.06
    赡
    -0.06
    .environ
    -0.06
    cean
    -0.06
    qui
    -0.06
    æĢ§åĬŁèĥ½
    -0.06
    Ñģлей
    -0.05
    injau
    -0.05
    POSITIVE LOGITS
    chein
    0.06
    é¡¿
    0.05
    éĶĻä½į
    0.05
    lint
    0.05
    exact
    0.05
    ÙĬÙĦ
    0.05
     indic
    0.05
     compatibles
    0.05
    宿
    0.05
    è¿ijäºĨ
    0.05
    Activations Density 0.101%

    No Known Activations