© 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. 18720
    Prev
    Next
    INDEX
    Explanations

    piston turbine rotor diaphragm turn

    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
    éļħ
    -0.06
    æłij人
    -0.06
    Displayed
    -0.06
    aghetti
    -0.06
    æīĵ好
    -0.06
    åĨħè¿Ľè¡Į
    -0.06
    urts
    -0.06
    çī¹å¤§
    -0.06
    ampire
    -0.06
     Weiner
    -0.06
    POSITIVE LOGITS
    æīĭä¸ĬçļĦ
    0.05
    Calendar
    0.05
    件
    0.05
    ca
    0.05
    Benchmark
    0.05
    ãģĭãģı
    0.05
     cal
    0.05
    æ§Ľ
    0.05
    preise
    0.05
    æīĭ
    0.05
    Activations Density 0.161%

    No Known Activations