© 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. 18355
    Prev
    Next
    INDEX
    Explanations

    ego or eg

    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
    beck
    -0.06
     Gale
    -0.06
    ewa
    -0.05
    -ahead
    -0.05
    ensation
    -0.05
    Ñħодила
    -0.05
    else
    -0.05
    elsea
    -0.05
    à¦ķার
    -0.05
    éĺģ
    -0.05
    POSITIVE LOGITS
    hip
    0.06
    dann
    0.06
    son
    0.06
    -sized
    0.06
    oper
    0.06
    yst
    0.06
    ÑĮ
    0.06
    dam
    0.06
    个éĹ®é¢ĺ
    0.06
     ego
    0.06
    Activations Density 0.001%

    No Known Activations