© 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. 19538
    Prev
    Next
    INDEX
    Explanations

    medical documentation

    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
    apel
    -0.07
    esa
    -0.07
    第ä¸ĢæŶéĹ´
    -0.07
    åıĬæŶçļĦ
    -0.07
    åıĬæŶå¤ĦçIJĨ
    -0.06
    å¤ĦçIJĨåIJİ
    -0.06
    åıĬæŶåIJij
    -0.06
    emet
    -0.06
     Haag
    -0.06
     Rossi
    -0.06
    POSITIVE LOGITS
    .constructor
    0.05
    åĬĽå£«
    0.05
    çĶ
    0.05
    entif
    0.05
    side
    0.05
    venta
    0.05
    jav
    0.05
    بط
    0.05
    没æľīå¿ħè¦ģ
    0.04
    侧éĿ¢
    0.04
    Activations Density 0.006%

    No Known Activations