© 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. 17002
    Prev
    Next
    INDEX
    Explanations

    society

    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
    er
    -0.10
     سÙĬÙħا
    -0.07
    nable
    -0.07
    erken
    -0.06
    erer
    -0.06
    atak
    -0.06
     ìĿ¸íķ´
    -0.06
    کت
    -0.06
    ä¹ıåĬĽ
    -0.05
    athan
    -0.05
    POSITIVE LOGITS
    à¸ĩาม
    0.07
    rides
    0.06
    atos
    0.06
    ÙĤÙī
    0.06
    ungsweise
    0.06
    ÙĪتر
    0.05
    ê°ģ
    0.05
    ä¸īçŃī
    0.05
    enaus
    0.05
    衣裳
    0.05
    Activations Density 0.020%

    No Known Activations