© 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. 20820
    Prev
    Next
    INDEX
    Explanations

    people and their relationships

    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
     nexus
    -0.05
     those
    -0.05
    ä¸İä»ĸ人
    -0.05
     string
    -0.05
    `
    -0.05
    string
    -0.05
    以ä¸ĬçļĦ
    -0.05
     ya
    -0.04
    those
    -0.04
    POSITIVE LOGITS
    åIJįåŃĹåı«
    0.07
    并åıĸå¾Ĺ
    0.07
    èĤ¡ä¸ľä¿¡æģ¯
    0.07
    æĽ´åIJį
    0.06
    ernes
    0.06
    -most
    0.06
    ONS
    0.06
    avons
    0.06
    ncer
    0.06
    esten
    0.06
    Activations Density 0.019%

    No Known Activations