© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20111
    Prev
    Next
    INDEX
    Explanations

    The letter 'B' followed by delimiters

    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
     independence
    -0.06
    asa
    -0.06
    æg
    -0.05
    ä¸Ģé¡¿
    -0.05
    æĦŁ
    -0.05
    én
    -0.05
    uru
    -0.05
    ExceptionHandler
    -0.05
     Independence
    -0.05
    ual
    -0.05
    POSITIVE LOGITS
    sters
    0.07
    iards
    0.06
    sehen
    0.06
    affles
    0.06
    lisi
    0.06
    Ñĩайно
    0.06
    Ñģп
    0.06
    antro
    0.06
    tuk
    0.06
    亢
    0.06
    Activations Density 0.032%

    No Known Activations