© 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. 22202
    Prev
    Next
    INDEX
    Explanations

    management tools and systems

    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
    çīĪ车åŀĭ
    -0.06
     عرضÙĩ
    -0.06
    ommen
    -0.06
    ported
    -0.06
    olta
    -0.06
     Access
    -0.05
    ilities
    -0.05
    alai
    -0.05
    磼
    -0.05
    fusion
    -0.05
    POSITIVE LOGITS
    ewis
    0.06
    zur
    0.05
    çī©æĸĻ
    0.05
    sey
    0.05
    æĻĹ
    0.05
    زÙħ
    0.05
    åĬłéĩį
    0.05
     endure
    0.05
    aven
    0.05
     mont
    0.05
    Activations Density 0.011%

    No Known Activations