© 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. 20437
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    леÑģ
    -0.07
    opp
    -0.06
    atrici
    -0.06
    boo
    -0.06
    alous
    -0.06
    tera
    -0.06
    eceÄŁini
    -0.06
    egger
    -0.06
    teres
    -0.06
    bev
    -0.06
    POSITIVE LOGITS
    è¾ħ
    0.05
    yme
    0.05
    оÑģÑĤа
    0.05
    iple
    0.05
    hren
    0.05
    ä¸ĩå¹´
    0.05
    çļĦæ°Ķè´¨
    0.05
    expire
    0.05
    olph
    0.05
    GNU
    0.05
    Activations Density 0.000%

    No Known Activations