© 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. 17281
    Prev
    Next
    INDEX
    Explanations

    list item number

    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
    AINS
    -0.06
    kaw
    -0.06
    atinum
    -0.06
     spra
    -0.05
    Ú©ÛĮد
    -0.05
    amo
    -0.05
    IRON
    -0.05
    YPD
    -0.05
    iron
    -0.05
    oin
    -0.05
    POSITIVE LOGITS
    ãģ³
    0.06
     /*!
    0.06
    bundet
    0.05
     thee
    0.05
     na
    0.05
     Na
    0.05
    erna
    0.05
     physical
    0.05
    ochond
    0.05
    å¼¹
    0.05
    Activations Density 0.014%

    No Known Activations