© 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. 17777
    Prev
    Next
    INDEX
    Explanations

    human and earth civilizations

    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
    仪
    -0.06
    رØŃ
    -0.06
    åıįæŃ£
    -0.05
    ¥
    -0.05
    ahl
    -0.05
     Manaus
    -0.05
    ’
    -0.05
     âĪ
    -0.05
    -dem
    -0.05
    å®ļåIJij
    -0.05
    POSITIVE LOGITS
    ellas
    0.07
    cept
    0.07
    ç§į
    0.07
    èħĬ
    0.06
    æľŃ
    0.06
    cern
    0.06
    eras
    0.06
    ugen
    0.06
    egr
    0.06
    епен
    0.06
    Activations Density 0.002%

    No Known Activations