© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20443
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
    æ¼±
    -0.06
    ,$
    -0.05
     Ñĩем
    -0.05
    inster
    -0.05
     journ
    -0.05
    åIJ«æľī
    -0.05
    inkel
    -0.05
     rem
    -0.05
    æłĪéģĵ
    -0.05
     carr
    -0.05
    POSITIVE LOGITS
    rien
    0.07
    ebas
    0.06
    éĤ£æł·
    0.06
    ik
    0.06
    è¿Ļæł·ä¸Ģç§į
    0.06
    reven
    0.06
     berupa
    0.05
    schild
    0.05
     Unabhäng
    0.05
     Fairfield
    0.05
    Activations Density 0.011%

    No Known Activations