© 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. 16918
    Prev
    Next
    INDEX
    Explanations

    code return

    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
    Ðijе
    -0.05
    æijĦå½±
    -0.05
    ainte
    -0.05
     ingredients
    -0.05
    çĴ§
    -0.05
    ability
    -0.05
    ceipt
    -0.05
    ÑĻи
    -0.05
    ÑıÑģ
    -0.05
    .microsoft
    -0.05
    POSITIVE LOGITS
    ifer
    0.06
    hout
    0.06
    venes
    0.06
    ابر
    0.06
    æĹłæįŁ
    0.06
    æĹ©å·²ç»ı
    0.06
    åħĭéĩĮ
    0.06
     opini
    0.06
    å·²ç»ıè¿Ľåħ¥
    0.05
    åĪĨ许
    0.05
    Activations Density 0.031%

    No Known Activations