© 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. 20614
    Prev
    Next
    INDEX
    Explanations

    meaning and identity

    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
    elves
    -0.06
     trend
    -0.06
    UTES
    -0.06
    Ñħай
    -0.06
    ICY
    -0.06
    rk
    -0.06
    yor
    -0.06
    æľīéģĵ
    -0.06
    trend
    -0.05
     altına
    -0.05
    POSITIVE LOGITS
     his
    0.06
    ä¹ĭ忧
    0.06
     himself
    0.05
    оÑĩÑĮ
    0.05
    tur
    0.05
    类似
    0.05
    urst
    0.05
     seinen
    0.05
    pile
    0.05
    his
    0.05
    Activations Density 0.008%

    No Known Activations