© 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. 18492
    Prev
    Next
    INDEX
    Explanations

    bir, 1, or tort

    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
    ener
    -0.06
    å²Ń
    -0.06
    artner
    -0.06
    éĢļ
    -0.06
    lege
    -0.06
    ucceed
    -0.06
    alanya
    -0.06
    ively
    -0.06
    hez
    -0.06
    ional
    -0.06
    POSITIVE LOGITS
    ÛĮ
    0.08
    è´¨çļĦ
    0.07
    çļĦ
    0.07
    er
    0.07
    nya
    0.06
    ly
    0.06
    erb
    0.06
    cing
    0.06
    çļĦçĭĢæ³ģ
    0.06
    skal
    0.06
    Activations Density 0.001%

    No Known Activations