© 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. 16885
    Prev
    Next
    INDEX
    Explanations

    java.util imports

    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
    Not in Any Lists

    No Comments

    Negative Logits
     F
    -0.06
    iving
    -0.05
     pul
    -0.05
     D
    -0.05
    ìĹIJ
    -0.05
    ÙĦÙģ
    -0.05
     P
    -0.05
     eq
    -0.05
    -0.05
    ments
    -0.05
    POSITIVE LOGITS
    à¹Ħหรà¹Ī
    0.08
    eszcze
    0.08
    поÑĢÑĤа
    0.07
    гоÑĢа
    0.07
    åıĬåħ¶èĩªåĬ¨åĮĸ
    0.07
    ุà¸ĩ
    0.07
    æĬĬ头
    0.07
    åѦåĴĮ
    0.07
    apphire
    0.07
     ulang
    0.07
    Activations Density 0.008%

    No Known Activations