© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18115
    Prev
    Next
    INDEX
    Explanations

    ascertained that

    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
    -0.06
    acia
    -0.06
    åIJ¦åĪĻ
    -0.05
    ond
    -0.05
    ä¹īçļĦ
    -0.05
     nghĩa
    -0.05
    aca
    -0.04
     indem
    -0.04
     mis
    -0.04
    chi
    -0.04
    POSITIVE LOGITS
    çłĶ究表æĺİ
    0.07
    ìŀħ
    0.06
    utow
    0.06
     stadig
    0.06
    à¸ŀา
    0.06
    èº
    0.06
    utt
    0.06
    werp
    0.06
    ergeb
    0.06
    åĬłæĭ¿å¤§
    0.06
    Activations Density 0.082%

    No Known Activations