© 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. 17874
    Prev
    Next
    INDEX
    Explanations

    . or code

    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
    rosso
    -0.06
     potentially
    -0.06
     potenz
    -0.06
    åħ¨æĸĩéĺħ读
    -0.06
    assel
    -0.06
    åħ·æľīä¸Ģå®ļçļĦ
    -0.06
    sek
    -0.06
    à¹īà¸Ń
    -0.06
    izin
    -0.06
    ettle
    -0.06
    POSITIVE LOGITS
    æĤ£
    0.06
    ung
    0.06
    éĵ¸
    0.05
     permanent
    0.05
    强
    0.05
    å¼ĥ
    0.05
    被æī§è¡Į
    0.05
    sens
    0.05
    ç²¹
    0.05
     Permanent
    0.05
    Activations Density 0.027%

    No Known Activations