© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18122
    Prev
    Next
    INDEX
    Explanations

    someone or somebody

    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
    Äħg
    -0.06
    izi
    -0.06
    åģ¿
    -0.06
    onis
    -0.06
    亡
    -0.06
    ç½ķ
    -0.06
    angen
    -0.05
    essin
    -0.05
    çīĪ
    -0.05
    ango
    -0.05
    POSITIVE LOGITS
    cale
    0.05
    æĹ¥å¸¸
    0.05
     benchmark
    0.05
    dater
    0.05
    jel
    0.05
    ç³»ç»Łè¿Ľè¡Į
    0.05
    å¯Ĩ度
    0.05
    umm
    0.05
    iron
    0.05
    benchmark
    0.05
    Activations Density 0.042%

    No Known Activations