© 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. 18146
    Prev
    Next
    INDEX
    Explanations

    garden and farm products

    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
    Basket
    -0.06
     Head
    -0.06
     khai
    -0.05
    íĮĮ
    -0.05
    iesta
    -0.05
    kirchen
    -0.05
     choice
    -0.05
     Basket
    -0.05
    åıijå±ķä¸İ
    -0.05
    atts
    -0.05
    POSITIVE LOGITS
    è´Ń
    0.06
    æī¿è¯º
    0.06
    éĹ°
    0.05
    arget
    0.05
    ord
    0.05
    éķ¿æķĪ
    0.05
    å¤ļä½į
    0.05
    ä¸įéĢĢ
    0.05
    å±Ĩ
    0.05
    reuse
    0.05
    Activations Density 0.016%

    No Known Activations