© 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. 16670
    Prev
    Next
    INDEX
    Explanations

    background and circumstances

    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
    rol
    -0.06
    cesa
    -0.06
    hofer
    -0.06
    íĨł
    -0.05
     karakter
    -0.05
    è§Ĵèī²
    -0.05
     never
    -0.05
    è§Ĵèī²çļĦ
    -0.05
     rem
    -0.05
     lado
    -0.05
    POSITIVE LOGITS
    çļĦèĥĮæĻ¯
    0.06
    iddel
    0.05
     Background
    0.05
    idle
    0.05
     BACKGROUND
    0.05
    Background
    0.05
    ãģĺãĤģãģ¦
    0.05
     Guards
    0.05
    enza
    0.05
    ä»ĸåij½
    0.05
    Activations Density 0.002%

    No Known Activations