© 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. 16933
    Prev
    Next
    INDEX
    Explanations

    game features

    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
    ally
    -0.06
    ac
    -0.06
    eger
    -0.05
     po
    -0.05
    antinya
    -0.05
     al
    -0.05
    tridge
    -0.05
     ac
    -0.05
     afflicted
    -0.05
    æľīéĻIJåħ¬åı¸
    -0.05
    POSITIVE LOGITS
    isan
    0.06
    ÃŃna
    0.06
    rés
    0.06
    cách
    0.06
    ой
    0.06
    rát
    0.05
     menú
    0.05
     Kut
    0.05
    isons
    0.05
    åİĨåı²å°ı说
    0.05
    Activations Density 0.001%

    No Known Activations