© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19293
    Prev
    Next
    INDEX
    Explanations

    together

    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
    ohn
    -0.06
     ÑģобÑĸ
    -0.06
    fern
    -0.06
    å¸Ĥå§Ķåī¯ä¹¦è®°
    -0.06
    hopefully
    -0.06
    anded
    -0.06
    unction
    -0.06
    è¿ĶåĽŀåĪĹ表
    -0.06
    empat
    -0.05
    æł©æł©å¦ĤçĶŁ
    -0.05
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.06
    æķĻ
    0.06
    ders
    0.05
    stw
    0.05
    çģ°
    0.05
    olja
    0.05
    çĮ¶
    0.05
    仪
    0.05
    Ø£ÙĬ
    0.05
     presence
    0.05
    Activations Density 0.002%

    No Known Activations