© 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. 16787
    Prev
    Next
    INDEX
    Explanations

    Scripps Research Institute

    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
    infra
    -0.05
    aldo
    -0.05
     anyone
    -0.05
    ä»Ģä¹Īåij¢
    -0.05
    ingkan
    -0.05
    afür
    -0.05
    ç¦ıæ°Ķ
    -0.05
    ceans
    -0.05
     doctrine
    -0.04
    omez
    -0.04
    POSITIVE LOGITS
    ç¡®æľī
    0.07
    ä¸Ģçľĭ
    0.06
    çķĻ念
    0.06
    áver
    0.06
    ikin
    0.06
    raison
    0.06
    esion
    0.06
    ÑĩиÑĤа
    0.06
    uver
    0.06
    endid
    0.06
    Activations Density 0.004%

    No Known Activations