© 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. 17125
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
    å¦Ĥ鼨
    -0.06
    loh
    -0.06
    idal
    -0.06
    á»ĩp
    -0.06
    oud
    -0.06
     наÑģ
    -0.06
     mú
    -0.06
    ording
    -0.06
    ç¦ıåħĭæĸ¯
    -0.06
    issen
    -0.05
    POSITIVE LOGITS
     lý
    0.06
     typeof
    0.06
    论
    0.05
    çĦī
    0.05
    ator
    0.05
     keer
    0.05
    æľº
    0.05
    ë¡ł
    0.05
    æĥĬ
    0.05
    знание
    0.05
    Activations Density 0.041%

    No Known Activations