© 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. 20888
    Prev
    Next
    INDEX
    Explanations

    aging and lifespan

    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
    ort
    -0.06
    imo
    -0.05
    æŀī
    -0.05
    L
    -0.05
    inga
    -0.05
     blocked
    -0.05
    edis
    -0.05
    磩
    -0.05
    azi
    -0.05
     infringement
    -0.05
    POSITIVE LOGITS
     rejuven
    0.07
    æĬĹè¡°èĢģ
    0.07
    noch
    0.06
     života
    0.06
    /Branch
    0.06
    å·¥é¾Ħ
    0.06
    åIJĦé¡¹å·¥ä½ľçļĦ
    0.05
    baugh
    0.05
    éķ¿å¯¿
    0.05
    -char
    0.05
    Activations Density 0.056%

    No Known Activations