© 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. 19759
    Prev
    Next
    INDEX
    Explanations

    dates and 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
    uada
    -0.05
    ston
    -0.05
    ict
    -0.05
    ä¸ĭæīĭ
    -0.05
    rens
    -0.05
    à¹Īà¸Ļ
    -0.05
    æĪĸ以
    -0.05
    rais
    -0.05
    ä¸ĭåĪ°
    -0.05
    è½®åĪ°
    -0.05
    POSITIVE LOGITS
    èĢĮèµ·
    0.06
    å°½ãģı
    0.06
     rehe
    0.06
    emat
    0.06
     overd
    0.06
    à¸Ńà¸ļ
    0.06
    бÑĥдÑĮÑĤе
    0.06
    ackets
    0.06
    apan
    0.05
    å©ķ
    0.05
    Activations Density 0.006%

    No Known Activations