© 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. 18359
    Prev
    Next
    INDEX
    Explanations

    references, services, defaultReferences

    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
    è¿Ļä¸ī个
    -0.11
    è¿Ļä¸ī
    -0.10
    è¿Ļä¸īç§į
    -0.10
     three
    -0.09
    ä¸ī个
    -0.09
    ä¸īç§į
    -0.09
    çļĦä¸ī个
    -0.09
     Three
    -0.09
    Three
    -0.08
    ä¸īåĢĭ
    -0.08
    POSITIVE LOGITS
     Doppel
    0.07
    åį¤
    0.06
    orse
    0.06
     twin
    0.06
    bior
    0.05
    ouble
    0.05
    uers
    0.05
    ξαν
    0.05
    akov
    0.05
    à¹īาà¸ĩ
    0.05
    Activations Density 0.006%

    No Known Activations