© 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. 17750
    Prev
    Next
    INDEX
    Explanations

    newly introduced leagues or sequels

    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
    iale
    -0.06
    iega
    -0.05
    é¾Ħ
    -0.05
    ige
    -0.05
    å®ļæł¼
    -0.05
    yeah
    -0.05
    èĤ¢
    -0.05
     gelang
    -0.05
     starred
    -0.05
    西æŀĹ
    -0.05
    POSITIVE LOGITS
    ستر
    0.06
     renewed
    0.06
    modern
    0.06
     nouvelles
    0.06
     moderno
    0.06
    çļĦçݰ代
    0.06
    apé
    0.06
     revived
    0.06
    çݰ代
    0.06
    رÙĬØ·
    0.06
    Activations Density 0.412%

    No Known Activations