© 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. 19450
    Prev
    Next
    INDEX
    Explanations

    abandoned

    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
     Howell
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    lector
    -0.06
     Leistung
    -0.06
    å°ĸçļĦ
    -0.05
    teil
    -0.05
    ç«ĭãģ¦
    -0.05
    ignon
    -0.05
    大马
    -0.05
    ìķ¼
    -0.05
    POSITIVE LOGITS
    ding
    0.06
    fert
    0.06
     abandon
    0.06
    ong
    0.06
    ration
    0.06
     اختÛĮار
    0.05
    prü
    0.05
    å¼ĥ
    0.05
    anaan
    0.05
    istribu
    0.05
    Activations Density 0.007%

    No Known Activations