© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22108
    Prev
    Next
    INDEX
    Explanations

    English language references

    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
    اØŃ
    -0.06
     Format
    -0.06
    atici
    -0.06
    elit
    -0.06
    erweise
    -0.06
    æĺ¯ä¸Ģ家éĽĨ
    -0.06
     also
    -0.06
    æł·åŃIJ
    -0.06
     format
    -0.06
     McL
    -0.06
    POSITIVE LOGITS
    人åķĬ
    0.05
    ä¸įå®ĮçļĦ
    0.05
    zuge
    0.05
    å½±
    0.05
    Ùģاء
    0.05
    ija
    0.05
     relentlessly
    0.05
    naan
    0.05
    令
    0.05
     Schatten
    0.05
    Activations Density 0.005%

    No Known Activations