© 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. 19151
    Prev
    Next
    INDEX
    Explanations

    that followed by i

    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
    ÑģаÑĨии
    -0.07
    åıijåĩºçļĦ
    -0.06
    chet
    -0.06
    uhan
    -0.06
    kamer
    -0.06
     اÙĨÙĩا
    -0.06
    apura
    -0.06
    idencia
    -0.06
    -sama
    -0.06
    åĽŀå¿Ĩ
    -0.06
    POSITIVE LOGITS
    akh
    0.05
    колÑĮ
    0.05
    以åıĬ对
    0.05
    åħ¶ä¸º
    0.05
    addock
    0.05
     (
    0.05
    кÑģ
    0.04
    åĩĨå¤ĩäºĨ
    0.04
    -like
    0.04
    ↵
    0.04
    Activations Density 0.002%

    No Known Activations