© 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. 19110
    Prev
    Next
    INDEX
    Explanations

    white snow

    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
    èµĦ
    -0.05
    kozó
    -0.05
     feast
    -0.05
    alat
    -0.05
    prav
    -0.05
    اØŃ
    -0.05
    ä½ĵ
    -0.05
    atum
    -0.05
    koz
    -0.05
    ÑĥÑĩ
    -0.05
    POSITIVE LOGITS
    æİ¥ä¸ĭ
    0.06
    顶ä¸Ĭ
    0.06
    пеÑĢеди
    0.05
    OLA
    0.05
    ,,,
    0.05
    ówczas
    0.05
    otty
    0.05
     izol
    0.05
    ],'
    0.05
     prij
    0.05
    Activations Density 0.001%

    No Known Activations