© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22603
    Prev
    Next
    INDEX
    Explanations

    time zone abbreviations

    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
    Negative Logits
    éĴ±äºĨ
    -0.06
     ranh
    -0.06
    artz
    -0.06
    leges
    -0.05
    enda
    -0.05
    iale
    -0.05
    andes
    -0.05
    gle
    -0.05
    iglia
    -0.05
    icer
    -0.05
    POSITIVE LOGITS
    徨
    0.06
    dem
    0.06
     repl
    0.05
    å¯Ħ
    0.05
    oug
    0.05
    ä¸ĭæľŁ
    0.05
    du
    0.05
     gerecht
    0.05
    èĬ±èIJ½
    0.05
    tu
    0.05
    Activations Density 0.023%

    No Known Activations