© 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. 16773
    Prev
    Next
    INDEX
    Explanations

    anxiety

    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
    就走
    -0.06
     despla
    -0.06
    çĤ¹è¿Ľè¡Į
    -0.06
    å¾ĢæľŁç²¾å½©
    -0.06
    ìļ´ëį°
    -0.06
    ľa
    -0.05
    istle
    -0.05
    è¿ŀçĿĢ
    -0.05
    ä¸ļ
    -0.05
    pond
    -0.05
    POSITIVE LOGITS
    akat
    0.06
    anut
    0.05
     recourse
    0.05
    apt
    0.05
    åįij
    0.05
     overlapping
    0.05
    atoon
    0.05
     advent
    0.05
    åĪĢåŃIJ
    0.05
    ouch
    0.05
    Activations Density 0.007%

    No Known Activations