© 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. 18412
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    лей
    -0.07
    rit
    -0.07
    etros
    -0.06
    zeci
    -0.06
     **:**
    -0.06
    jenigen
    -0.06
    tima
    -0.06
     Hinblick
    -0.06
     trai
    -0.06
    ä¸īå²ģ
    -0.06
    POSITIVE LOGITS
    а
    0.06
    ellig
    0.06
    اÙĤ
    0.06
    quinho
    0.06
    åħ¶ä¸İ
    0.06
    ungs
    0.06
    ÙĤÛĮ
    0.06
    emic
    0.05
    led
    0.05
    ад
    0.05
    Activations Density 0.054%

    No Known Activations