© 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. 17929
    Prev
    Next
    INDEX
    Explanations

    decimal places

    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
    intérêt
    -0.06
    ä¹ł
    -0.05
     maths
    -0.05
    astique
    -0.05
     matem
    -0.05
    Ùĥار
    -0.05
    amai
    -0.05
    ampil
    -0.05
     wed
    -0.05
    ÐĵеÑĢ
    -0.05
    POSITIVE LOGITS
    è¯Ń
    0.06
    ов
    0.05
     presses
    0.05
    岸
    0.05
    ãģ£ãģ±
    0.05
     AssertionError
    0.05
    çľĭä½ł
    0.05
     допÑĥÑģка
    0.05
    åĽĽåij¨
    0.05
    è¯ŃçļĦ
    0.05
    Activations Density 0.004%

    No Known Activations