© 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. 17370
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts

    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
    unate
    -0.06
     Especial
    -0.06
    รุà¸ģ
    -0.06
    ↵     ↵
    -0.06
    ืà¹īà¸Ń
    -0.05
     especial
    -0.05
    ish
    -0.05
    _reserved
    -0.05
    ÑģмоÑĤÑĢиÑĤе
    -0.05
    пÑĥÑģ
    -0.05
    POSITIVE LOGITS
    å®Ŀ
    0.06
    ãģªãĤĭ
    0.05
    amkan
    0.05
    ÏĥÏĦεί
    0.05
    è°Ĵ
    0.05
    ree
    0.05
     ned
    0.05
    大使
    0.05
    Ed
    0.05
    Traits
    0.05
    Activations Density 0.003%

    No Known Activations