© 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. 20192
    Prev
    Next
    INDEX
    Explanations

    writing to files

    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
    áh
    -0.07
    husus
    -0.06
    istiwa
    -0.06
    ä¸ĢæŶ
    -0.06
    fahrens
    -0.06
    ÑħнÑĥÑĤÑĮ
    -0.06
    æĪIJåħ¨
    -0.06
     personali
    -0.06
     pessoais
    -0.05
    ène
    -0.05
    POSITIVE LOGITS
    éĭŃ
    0.06
    解çłģ
    0.06
    ing
    0.05
    pression
    0.05
    mens
    0.05
    oire
    0.05
    erman
    0.05
    prost
    0.05
    é²ľ
    0.05
    awali
    0.05
    Activations Density 0.011%

    No Known Activations