© 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. 17563
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation or 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
    å½¹
    -0.07
    侧
    -0.06
    otope
    -0.06
    æij¹
    -0.06
    midd
    -0.06
    anha
    -0.05
    erture
    -0.05
    骸
    -0.05
    ô
    -0.05
    uble
    -0.05
    POSITIVE LOGITS
     etc
    0.06
    insi
    0.06
    aller
    0.06
    å¼ĤçļĦ
    0.05
    alloc
    0.05
    rund
    0.05
    ilmington
    0.05
    åĮ
    0.05
    enj
    0.05
    à§įযা
    0.05
    Activations Density 0.010%

    No Known Activations