© 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. 18764
    Prev
    Next
    INDEX
    Explanations

    brothers Jason

    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
    ÙĬØŃØ©
    -0.06
    åħ¥å¾®
    -0.05
    ç©
    -0.05
    æŁĶ
    -0.05
    çģµ
    -0.05
    asic
    -0.05
    bout
    -0.05
    æĬķèµĦæĪĸ
    -0.05
     Loose
    -0.05
    èij
    -0.05
    POSITIVE LOGITS
    lop
    0.06
    æīĭæıIJ
    0.06
    ád
    0.06
     yen
    0.06
    elas
    0.06
    ×ķ׳
    0.05
    áĬIJ
    0.05
     uten
    0.05
    apon
    0.05
    mr
    0.05
    Activations Density 0.001%

    No Known Activations