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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19640
    Prev
    Next
    INDEX
    Explanations

    sometimes greatest way

    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
    engi
    -0.07
    ç¾İ好çļĦæľªæĿ¥
    -0.07
    illot
    -0.06
     ervan
    -0.06
    enni
    -0.06
    ÑĥÑĤа
    -0.06
     someday
    -0.06
    çĻľ
    -0.06
    عاÙĨ
    -0.06
    hog
    -0.06
    POSITIVE LOGITS
    éĢĤ
    0.07
    éģ©
    0.06
    æĶ¾æīĭ
    0.05
    yr
    0.05
    .self
    0.05
    ú
    0.05
    ä¸įéľĢè¦ģ
    0.05
    æĶ¾ä¸ĭ
    0.05
     what
    0.05
    åħ¬
    0.05
    Activations Density 0.046%

    No Known Activations