© 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. 17814
    Prev
    Next
    INDEX
    Explanations

    when, while, at, on

    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
    çĤ¹å°ı
    -0.06
    çĶ¨å°ı
    -0.06
    omething
    -0.05
     Äijắc
    -0.05
    ayaan
    -0.05
     close
    -0.05
     minder
    -0.05
    å¼ĢçªĹ
    -0.05
     good
    -0.05
    cope
    -0.05
    POSITIVE LOGITS
    adge
    0.06
    Trap
    0.06
    大亨
    0.06
    ланд
    0.06
    ÑģÑİ
    0.05
    é¡
    0.05
    assic
    0.05
    çĮ
    0.05
    egin
    0.05
    è»Į
    0.05
    Activations Density 0.001%

    No Known Activations