© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19521
    Prev
    Next
    INDEX
    Explanations

    code that returns boolean values or ends code blocks

    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
    ück
    -0.05
    klad
    -0.05
    semble
    -0.05
    owitz
    -0.05
    oub
    -0.05
    å¸ĪçĶŁçļĦ
    -0.05
    orton
    -0.05
    rought
    -0.05
    åħ³æ³¨çļĦçĦ¦çĤ¹
    -0.05
     conver
    -0.05
    POSITIVE LOGITS
     outlet
    0.06
    elite
    0.06
    ä¸Ńå¿ĥçŃī
    0.06
     Outlet
    0.06
    adena
    0.05
     reserva
    0.05
    æĸ°æ¦Ĥ念
    0.05
    æĸ°ç¤¾
    0.05
     réserve
    0.05
    AMED
    0.05
    Activations Density 0.003%

    No Known Activations