© 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. 17372
    Prev
    Next
    INDEX
    Explanations

    manner, like, akin, analogy, similar

    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
    ä¸Ģåı·
    -0.06
    itation
    -0.06
    ijo
    -0.06
    å¹´æľŁ
    -0.06
     zir
    -0.06
    ennes
    -0.05
    isses
    -0.05
    åĺĺ
    -0.05
    éģ®
    -0.05
    aven
    -0.05
    POSITIVE LOGITS
    trä
    0.06
     technically
    0.06
    unte
    0.06
    acto
    0.05
     parlam
    0.05
    edan
    0.05
    ستÛĮ
    0.05
     sorte
    0.05
    addafi
    0.05
    ä¸ĥåįģäºĮ
    0.05
    Activations Density 0.025%

    No Known Activations