© 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. 20790
    Prev
    Next
    INDEX
    Explanations

    Diocese

    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
    ç¿»
    -0.05
    ä¸ij
    -0.05
    端
    -0.04
    Ø°ÙĬ
    -0.04
    æĮ¨
    -0.04
    éĢĢ
    -0.04
    延
    -0.04
    å®ļ
    -0.04
     Lap
    -0.04
     коÑĤоÑĢÑĭÑħ
    -0.04
    POSITIVE LOGITS
    ivate
    0.06
    伯
    0.06
    hov
    0.06
     vare
    0.06
    è¿Ľè¡Įä¸Ń
    0.06
    brew
    0.06
    estone
    0.06
    capture
    0.06
    çļĦéĢļ
    0.06
    halter
    0.06
    Activations Density 0.067%

    No Known Activations