© 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. 21338
    Prev
    Next
    INDEX
    Explanations

    numbers after operations

    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
    ikian
    -0.07
    ->[
    -0.06
    æĴ
    -0.06
    æĥ¹
    -0.06
    /XML
    -0.06
     grd
    -0.06
    quam
    -0.06
    alej
    -0.06
     cie
    -0.06
    nTo
    -0.06
    POSITIVE LOGITS
    åĨį次
    0.06
    ä¸įåĨį
    0.06
    illion
    0.05
    åĿIJ
    0.05
    è¿ĺæľīåħ¶ä»ĸ
    0.05
     again
    0.05
    åħ¶ä»ĸ
    0.05
    apt
    0.05
    iph
    0.05
    ear
    0.05
    Activations Density 0.004%

    No Known Activations