© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19465
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    åĮĸçļĦ
    -0.06
    bbe
    -0.05
    çļĦå°±æĺ¯
    -0.05
    )âĢ¦
    -0.05
    cer
    -0.05
    æī£
    -0.05
    å£ĵ
    -0.05
    ìĦľ
    -0.05
    issé
    -0.05
    çŃĭ
    -0.05
    POSITIVE LOGITS
    s
    0.07
    ingly
    0.07
    Ñĭ
    0.07
    大æĥĬ
    0.07
    ãģĬçŁ¥ãĤīãģĽ
    0.07
     feit
    0.06
    schild
    0.06
    à¸Ĭà¸Ļะ
    0.06
    roy
    0.06
    liness
    0.06
    Activations Density 0.003%

    No Known Activations